Peter Stone

Conference submission (2/1/02). Modeling Auction Price Uncertainty Using Boosting-based Conditional Density Estimation (2009)

Robert E. Schapire, Peter Stone, David Mcallester, Michael L. Littman, János A. Csirik

In complicated, interacting auctions, a fundamental problem is the prediction of prices of goods in the auctions, and more broadly, the modeling of uncertainty regarding these prices. In this paper,...

A General Purpose Task Specification Language for Bootstrap Learning (2009)

Ian Fasel, Michael Quinlan, Peter Stone

Reinforcement learning (RL) is an effective framework for online learning by autonomous agents. Most RL research focuses on domain-independent learning algorithms, requiring an expert human to define...

USING NEUROEVOLUTION APPROVED BY SUPERVISING COMMITTEE: (2009)

Aravind Gowrisankar, Risto Miikkulainen Supervisor, Peter Stone, To Amma

I would like to thank Risto Miikkulainen for his patient support during all stages of this thesis. Risto’s Neural Network class inspired me to start doing research in neuroevolution. Thanks to Ugo...

Brian StankiewiczReinforcement Learning In High-Diameter, Continuous Environments (2009)

Jefferson Provost, Jefferson Provost, Benjamin J. Kuipers, Risto Miikkulainen Supervisor, Raymond Mooney, Bruce Porter, ...

A couple of years ago someone forwarded me a link to an article interpreting Frodo’s quest in The Lord of the Rings as an allegory for writing and filing a dissertation (Lee, 2005). At the time, I...

TAMER: Training an Agent Manually via Evaluative Reinforcement (2009)

W. Bradley Knox, Peter Stone

Abstract—Though computers have surpassed humans at many tasks, especially computationally intensive ones, there are many tasks for which human expertise remains necessary and/or useful. For such...

Hierarchical Model-Based Reinforcement Learning: R-MAX + MAXQ (2009)

Nicholas K. Jong, Peter Stone

Hierarchical decomposition promises to help scale reinforcement learning algorithms naturally to real-world problems by exploiting their underlying structure. Model-based algorithms, which provided...

Domestic Interaction on a Segway Base (2009)

W. Bradley Knox, Juhyun Lee, Peter Stone

Abstract. To be useful in a home environment, an assistive robot needs to be capable of a broad range of interactive activities such as locating objects, following specific people, and distinguishing...

Online Kernel Selection for Bayesian Reinforcement Learning (2009)

Joseph Reisinger, Peter Stone, Risto Miikkulainen

Kernel-based Bayesian methods for Reinforcement Learning (RL) such as Gaussian Process Temporal Difference (GPTD) are particularly promising because they rigorously treat uncertainty in the value...

Online Multiagent Learning against Memory Bounded Adversaries (2009)

Doran Chakraborty, Peter Stone

Abstract. The traditional agenda in Multiagent Learning (MAL) has been to develop learners that guarantee convergence to an equilibrium in self-play or that converge to playing the best response...

CARVE: A Cognitive Agent for Resource Value Estimation (2009)

Jonathan Wildstrom, Peter Stone, Computer Sciences

Recent years have seen a growing push toward utilitycomputing [10, 6]. In this new paradigm, computation and memory are treated as a utility similar to electricity or wa-ter, and "service...

Multiagent Interactions in Urban Driving (2009)

Patrick Beeson, Bartley Gillan, Tarun Nimmagadda, Mickey Ristroph, David Li, Peter Stone

between fully autonomous vehicles. Unlike previous challenges, the Urban Challenge vehicles had to follow the California laws for driving, including properly handling traffic. This article presents...

Hierarchical Model-Based Reinforcement Learning: R-MAX + MAXQ (2009)

Nicholas K. Jong, Peter Stone

Hierarchical decomposition promises to help scale reinforcement learning algorithms naturally to real-world problems by exploiting their underlying structure. Model-based algorithms, which provided...

A Multiagent Approach to Autonomous Intersection Management (2009)

Kurt Dresner, Peter Stone

Artificial intelligence research is ushering in a new era of sophisticated, mass-market transportation technology. While computers can already fly a passenger jet better than a trained human pilot,...

Adaptive Tile Coding for Reinforcement Learning (2009)

Shimon Whiteson, Matthew E. Taylor, Peter Stone

• Most real-world reinforcement learning tasks have large or continuous state spaces • Table-based approaches are infeasible, need function approximators (FAs) instead • Many types of function...

ABSTRACT Autonomous Transfer for Reinforcement Learning (2009)

Matthew E. Taylor, Gregory Kuhlmann, Peter Stone

Recent work in transfer learning has succeeded in making reinforcement learning algorithms more efficient by incorporating knowledge from previous tasks. However, such methods typically must be...

Coach: A Machine Learning Approach (2009)

In Daniele Nardi, Martin Riedmiller, Claude Sammut, Soccer World, Cup Viii, ...

Abstract. The UT Austin Villa 2003 simulated online soccer coach was a first time entry in the RoboCup Coach Competition. In developing the coach, the main research focus was placed on treating...

• Limited vision � Limited communication (2009)

Peter Stone, Richard S. Sutton, Gregory Kuhlmann, Presented Maysam Heydari

� Challenges posed by RoboCup Soccer: � fully distributed, multi-agent domain with teammates and adversaries � Large state space

ABSTRACT Autonomous Transfer for Reinforcement Learning (2008)

Matthew E. Taylor, Gregory Kuhlmann, Peter Stone

Recent work in transfer learning has succeeded in making reinforcement learning algorithms more efficient by incorporating knowledge from previous tasks. However, such methods typically must be...

Instance-Based Action Models for Fast Action (2008)

Planning Mazda Ahmadi, Peter Stone

Abstract. Two main challenges of robot action planning in real domains are uncertain action effects and dynamic environments. In this paper, an instance-based action model is learned empirically by...

A RESERVATION-BASED MULTIAGENT SYSTEM FOR INTERSECTION CONTROL (2008)

Kurt Dresner, Peter Stone

Abstract: Traffic congestion is one of the leading causes of lost productivity and decreased standard of living in urban settings. Recent advances in artificial intelligence suggest that autonomous...

Long-term vs. Greedy Action Planning for Color Learning on a Mobile Robot (2008)

Mohan Sridharan, Peter Stone

Abstract: A major challenge to the deployment of mobile robots is the ability to function autonomously, learning appropriate models for environmental features and adapting those models in response to...

Online Coach Team (2008)

In Daniel Polani, Brett Browning, Andrea Bonarini, Kazuo Yoshida, Soccer World, ...

Abstract. The UT Austin Villa 2003 simulated online soccer coach was a first time entry in the RoboCup Coach Competition. In developing the coach, the main research focus was placed on treating...

Springer Verlag, 2008. Model-based Reinforcement Learning in a Complex Domain (2008)

Shivaram Kalyanakrishnan, Peter Stone, Yaxin Liu

Abstract. Reinforcement learning is a paradigm under which an agent seeks to improve its policy by making learning updates based on the experiences it gathers through interaction with the...

ÓÒÐÝ Û��Ò Ð���Ð� � ØÖ��Ò�Ò � ��Ø � � × �Ú��Ð��Ð � Ì�� × Ô�Ô�Ö (2008)

Shimon Whiteson, Risto Miikkulainen, Peter Stone, Nate Kohl, Kenneth O. Stanley

ÔÖ�×�ÒØ × � ÒÓÚ�Ð Ñ�Ø�Ó � �ÐÐ� � �Ë Æ��Ì Û� � � �ÜØ�Ò� × Ø�� Æ��Ì Ò�ÙÖÓ�ÚÓÐÙØ�ÓÒ Ñ�Ø�Ó � ØÓ...

TacTex-05: An (2008)

David Pardoe, Peter Stone, Mark Vanmiddlesworth

Abstract. Supply chains are ubiquitous in the manufacturing of many complex products. Traditionally, supply chains have been created through the interactions of human representatives of the companies...

Published online: (2008)

Charles Lee Isbell, Jr. Michael Kearns, Satinder Singh, Christian R. Shelton, Peter Stone, Dave Kormann, ...

Abstract We describe our development of Cobot, a novel software agent who lives in LambdaMOO, a popular virtual world frequented by hundreds of users. Cobot’s goal was to become an actual part of...

ABSTRACT Transfer via Inter-Task Mappings in Policy Search Reinforcement Learning (2008)

Matthew E. Taylor, Shimon Whiteson, Peter Stone

The ambitious goal of transfer learning is to accelerate learning on a target task after training on a different, but related, source task. While many past transfer methods have focused on...

Representation Transfer via Elaboration (2008)

Matthew E. Taylor, Peter Stone

A key component of any reinforcement learning (RL) algorithm is the underlying representation used by the agent for learning (e.g. the parameterization of its function approximator). Transfer...

Springer Verlag, 2007. Half Field Offense in RoboCup Soccer: A Multiagent Reinforcement Learning Case Study (2008)

Shivaram Kalyanakrishnan, Yaxin Liu, Peter Stone

Abstract. We present half field offense, a novel subtask of RoboCup simulated soccer, and pose it as a problem for reinforcement learning. In this task, an offense team attempts to outplay a defense...

Accelerating Search with Transferred Heuristics (2008)

Matthew E. Taylor, Gregory Kuhlmann, Peter Stone

A common goal for transfer learning research is to show that a learner can solve a source task and then leverage the learned knowledge to solve a target task faster than if it had learned the target...

Three Automated Stock-Trading Agents:A Comparative Study (2008)

Er A. Sherstov, Peter Stone

1 Introduction Automated stock trading is a burgeoning research area with important practical applica-tions. The advent of the Internet has radically transformed the nature of stock trading in most...

Comparing Two Action Planning Approaches for Color Learning on a Mobile Robot (2008)

Mohan Sridharan, Peter Stone

Abstract. A major challenge to the deployment of mobile robots in a wide range of tasks is the ability to function autonomously, learning appropriate models for environmental features and adapting...

Towards Eliminating Manual Color Calibration (2008)

In Itsuki Noda, Adam Jacoff, Ansgar Bredenfeld, Yasutake Takahashi, At Robocup, Mohan Sridharan, ...

Abstract. Color calibration is a time-consuming, and therefore costly requirement for most robot teams at RoboCup. This paper presents an approach for autonomous color learning on-board a mobile...

Springer Verlag, 2008. A Neural Network-Based Approach to Robot Motion Control (2008)

Uli Grasemann, Daniel Stronger, Peter Stone

Abstract. The joint controllers used in robots like the Sony Aibo are designed for the task of moving the joints of the robot to a given position. However, they are not well suited to the problem of...

Expectation-Based Vision for Self-Localization on a Legged Robot (2008)

Daniel Stronger, Peter Stone

This paper presents and empirically compares solutions to the problem of vision and self-localization on a legged robot. Specifically, given a series of visual images produced by a camera on-board...

Evolving Soccer Keepaway Players through Task Decomposition (2008)

Shimon Whiteson, Nate Kohl, Risto Miikkulainen, Peter Stone

Abstract. Complex control tasks can often be solved by decomposing them into hierarchies of manageable subtasks. Such decompositions require designers to decide how much human knowledge should be...

Polynomial Regression with Automated Degree: A Function Approximator for Autonomous Agents (2008)

Daniel Stronger, Peter Stone

Abstract. In order for an autonomous agent to behave robustly in a variety of environments, it must have the ability to learn approximations to many different functions. The function approximator...

Autonomous Planned Color Learning on a Legged Robot (2008)

Mohan Sridharan, Peter Stone

Abstract. Our research focuses on automating the color-learning process on-board a legged robot with limited computational and memory resources. A key defining feature of our approach is that instead...

Executive Summary (2008)

Dave Tuttle, Dave Tuttle, Prof Peter Stone, Peter Stone, Patrick Beeson, Tekin Meriçli, ...

not guarantee the accuracy or reliability of the information in this paper."

Published online: (2008)

Charles Lee Isbell, Jr. Michael Kearns, Satinder Singh, Christian R. Shelton, Peter Stone, Dave Kormann, ...

Abstract We describe our development of Cobot, a novel software agent who lives in LambdaMOO, a popular virtual world frequented by hundreds of users. Cobot’s goal was to become an actual part of...

Layered Learning towards Autonomic Computing (2008)

Peter Stone

Layered learning [2] is a general-purpose machine learning paradigm for complex domains in which learning a mapping directly from agents ’ sensors to their actuators is intractable. Given a...

Adaptive Tile Coding for Value Function Approximation (2008)

Shimon Whiteson, Matthew E. Taylor, Peter Stone

Reinforcement learning problems are commonly tackled by estimating the optimal value function. In many real-world problems, learning this value function requires a function approximator, which maps...

INTERNATIONAL JOURNAL OF c ○ 2007 Institute for Scientific INFORMATION AND SYSTEMS SCIENCES Computing and Information Volume 3, Number 3, Pages 510–525 PLANNING ACTIONS TO ENABLE COLOR LEARNING ON A MOBILE ROBOT (2008)

Mohan Sridharan, Peter Stone

Abstract. Color segmentation is a challenging yet integral subtask of mobile robot systems that use visual sensors, especially since such systems typically have limited computational and memory...

The Trading Agent Competition Supply Chain Management Scenario (TAC SCM) [Sadeh (2008)

David Pardoe, Peter Stone

This paper introduces TacTex-03, an agent designed to participate in the Trading Agent Competition Supply Chain Management Scenario (TAC SCM). As specified by this scenario, TacTex-03 acts as a...

In Lakemeyer, Sklar, Sorrenti, Takahashi, editors, RoboCup-2006: Robot Soccer World Cup X, pp. 72--85, Springer Verlag, 2007. Half Field Offense in RoboCup Soccer: A Multiagent Reinforcement Learning Case Study (2008)

Shivaram Kalyanakrishnan, Yaxin Liu, Peter Stone

Abstract. We present half field offense, a novel subtask of RoboCup simulated soccer, and pose it as a problem for reinforcement learning. In this task, an offense team attempts to outplay a defense...

Three Automated Stock-Trading Agents:A Comparative Study (2008)

Er A. Sherstov, Peter Stone

1 Introduction Automated stock trading is a burgeoning research area with important practical applica-tions. The advent of the Internet has radically transformed the nature of stock trading in most...

Transfer Learning and Intelligence: an Argument and Approach (2008)

Matthew E. Taylor, Gregory Kuhlmann, Peter Stone

Abstract. In order to claim fully general intelligence in an autonomous agent, the ability to learn is one of the most central capabilities. Classical machine learning techniques have had many...

Springer Verlag, 2007. Selective Visual Attention for Object Detection on a Legged Robot (2008)

Daniel Stronger, Peter Stone

Abstract. Autonomous robots can use a variety of sensors, such as sonar, laser range finders, and bump sensors, to sense their environments. Visual information from an onboard camera can provide...

Adaptive Tile Coding for Value Function Approximation (2008)

Shimon Whiteson, Matthew E. Taylor, Peter Stone

Reinforcement learning problems are commonly tackled by estimating the optimal value function. In many real-world problems, learning this value function requires a function approximator, which maps...

Temporal Difference and Policy Search Methods for Reinforcement Learning: An Empirical Comparison (2008)

Matthew E. Taylor, Shimon Whiteson, Peter Stone

Reinforcement learning (RL) methods have become popular in recent years because of their ability to solve complex tasks with minimal feedback. Both genetic algorithms (GAs) and temporal difference...

ABSTRACT Automatic Feature Selection in Neuroevolution (2008)

Shimon Whiteson, Risto Miikkulainen, Peter Stone, Nate Kohl

Feature selection is the process of finding the set of inputs to a machine learning algorithm that will yield the best performance. Developing a way to solve this problem automatically would make...

Coach: A Machine Learning Approach (2008)

In Daniele Nardi, Martin Riedmiller, Claude Sammut, Soccer World, Cup Viii, ...

Abstract. The UT Austin Villa 2003 simulated online soccer coach was a first time entry in the RoboCup Coach Competition. In developing the coach, the main research focus was placed on treating...

ABSTRACT Transfer via InterTask Mappings in Policy Search Reinforcement Learning (2008)

Matthew E. Taylor, Shimon Whiteson, Peter Stone

The ambitious goal of transfer learning is to accelerate learning on a target task after training on a different, but related, source task. While many past transfer methods have focused on...

An Autonomous Agent for Supply Chain Management Abstract (2008)

David Pardoe, Peter Stone

Supply Chain Management involves planning for the procurement of materials, assembly of finished products from these materials, and distribution of products to customers. The Trading Agent...

Transfer learning via inter-task mappings for temporal difference learning (2008)

Matthew E. Taylor, Peter Stone, Yaxin Liu, L. Littman

Temporal difference (TD) learning (Sutton and Barto, 1998) has become a popular reinforcement learning technique in recent years. TD methods, relying on function approximators to generalize learning...

Evolving Soccer Keepaway Players through Task Decomposition (2008)

Shimon Whiteson, Nate Kohl, Risto Miikkulainen, Peter Stone

Abstract. Complex control tasks can often be solved by decomposing them into hierarchies of manageable subtasks. Such decompositions require designers to decide how much human knowledge should be...

1 A Distributed Biconnectivity Check (2008)

Mazda Ahmadi, Peter Stone

Summary. For many distributed autonomous robotic systems, it is important to maintain communication connectivity among the robots. That is, each robot must be able to communicate with each other...

AT&T Labs — Research (2008)

Peter Stone, Manuela Veloso

Abstract. This paper presents layered learning, a hierarchical machine learning paradigm. Layered learning applies to tasks for which learning a direct mapping from inputs to outputs is intractable...

Accelerating Search with Transferred Heuristics (2008)

Matthew E. Taylor, Gregory Kuhlmann, Peter Stone

A common goal for transfer learning research is to show that a learner can solve a source task and then leverage the learned knowledge to solve a target task faster than if it had learned the target...

Evolving Soccer Keepaway Players through Task Decomposition (2008)

Shimon Whiteson, Nate Kohl, Risto Miikkulainen, Peter Stone

Abstract. Complex control tasks can often be solved by decomposing them into hierarchies of manageable subtasks. Such decompositions require designers to decide how much human knowledge should be...

ABSTRACT IFSA: Incremental Feature-Set Augmentation for Reinforcement Learning Tasks (2008)

Mazda Ahmadi, Matthew E. Taylor, Peter Stone

Reinforcement learning is a popular and successful framework for many agent-related problems because only limited environmental feedback is necessary for learning. While many algorithms exist to...

The Trading Agent Competition Supply Chain Management Scenario (TAC SCM) [Sadeh (2008)

David Pardoe, Peter Stone

This paper introduces TacTex-03, an agent designed to participate in the Trading Agent Competition Supply Chain Management Scenario (TAC SCM). As specified by this scenario, TacTex-03 acts as a...

Temporal Difference and Policy Search Methods for Reinforcement Learning: An Empirical Comparison (2008)

Matthew E. Taylor, Shimon Whiteson, Peter Stone

Reinforcement learning (RL) methods have become popular in recent years because of their ability to solve complex tasks with minimal feedback. Both genetic algorithms (GAs) and temporal difference...

Springer Verlag, 2008. Instance-Based Action Models for Fast Action Planning (2008)

Mazda Ahmadi, Peter Stone

Abstract. Two main challenges of robot action planning in real domains are uncertain action effects and dynamic environments. In this paper, an instance-based action model is learned empirically by...

: /www.ep.liu.se/ea/cis/1999/007/02/ The CMUnited-99 Simulator Team (2008)

Peter Stone, Manuela Veloso, Patrick Riley

Abstract. The CMUnited-98 simulator team became the 1998 RoboCup simulator league champion by winning all 8 of its games, outscoring opponents by a total of 66–0. CMUnited-99 builds upon the...

In Proc. Symposium on Abstraction, Reformulation, and Approximation (SARA-05) Function Approximation via Tile Coding: Automating Parameter Choice (2008)

Er A. Sherstov, Peter Stone

Abstract. Reinforcement learning (RL) is a powerful abstraction of sequential decision making that has an established theoretical foundation and has proven effective in a variety of small, simulated...

An Autonomous Agent for Supply Chain Management Abstract (2008)

David Pardoe, Peter Stone

Supply Chain Management involves planning for the procurement of materials, assembly of finished products from these materials, and distribution of products to customers. The Trading Agent...

A Neural Network-Based Approach to Robot Motion Control (2008)

In Visser, Springer Verlag, Uli Grasemann, Daniel Stronger, Peter Stone

Abstract. The joint controllers used in robots like the Sony Aibo are designed for the task of moving the joints of the robot to a given position. However, they are not well suited to the problem of...

Transfer Learning and Intelligence: an Argument and Approach (2008)

Matthew E. Taylor, Gregory Kuhlmann, Peter Stone

Abstract. In order to claim fully general intelligence in an autonomous agent, the ability to learn is one of the most central capabilities. Classical machine learning techniques have had many...

Detecting Motion in the World with a Moving Quadruped Robot (2008)

Peggy Fidelman, Thayne Coffman, Risto Miikkulainen, Peter Stone

Abstract. For a robot in a dynamic environment, the ability to detect motion is crucial. Although legs are arguably the most versatile means of locomotion for a robot, and thus the best suited to an...

Transfer learning via inter-task mappings for temporal difference learning (2008)

Matthew E. Taylor, Peter Stone, Yaxin Liu, L. Littman

Temporal difference (TD) learning (Sutton and Barto, 1998) has become a popular reinforcement learning technique in recent years. TD methods, relying on function approximators to generalize learning...

Acknowledgments (2008)

Michael David Bond, Kathryn S. Mckinley, Stephen M. Blackburn, Keshav Pingali, Peter Stone, Emmett Witchel, ...

I am deeply grateful to Kathryn McKinley for supporting and mentor-ing me in many ways. Kathryn has provided invaluable technical expertise and feedback even as we worked in new areas. She has been...

Transferring instances for model-based reinforcement learning (2008)

Matthew E. Taylor, Nicholas K. Jong, Peter Stone

Reinforcement learning agents typically require a significant amount of data before performing well on complex tasks. Transfer learning methods have made progress reducing sample complexity, but they...

Acknowledgments (2008)

Michael David Bond, Kathryn S. Mckinley, Stephen M. Blackburn, Keshav Pingali, Peter Stone, Emmett Witchel, ...

I am deeply grateful to Kathryn McKinley for supporting and mentor-ing me in many ways. Kathryn has provided invaluable technical expertise and feedback even as we worked in new areas. She has been...

Model-based reinforcement learning in a complex domain (2008)

Shivaram Kalyanakrishnan, Peter Stone, Yaxin Liu

Abstract. Reinforcement learning is a paradigm under which an agent seeks to improve its policy by making learning updates based on the experiences it gathers through interaction with the...

Diagnosing and Tolerating Bugs in Deployed Systems Committee: (2008)

Michael David Bond, Michael David Bond, Kathryn S. Mckinley, Stephen M. Blackburn, Keshav Pingali, Peter Stone, ...

I am deeply grateful to Kathryn McKinley for supporting and mentor-ing me in many ways. Kathryn has provided invaluable technical expertise and feedback even as we worked in new areas. She has been...

UT Austin Villa 2008: Standing On Two Legs (2008)

Todd Hester, Michael Quinlan, Peter Stone

In 2008, UT Austin Villa entered a team in the first Nao competition of the Standard Platform League of the RoboCup competition. The team had previous experience in RoboCup in the Aibo leagues. Using...

Diagnosing and Tolerating Bugs in Deployed Systems Committee: (2008)

Michael David Bond, Kathryn S. Mckinley, Stephen M. Blackburn, Keshav Pingali, Peter Stone, Emmett Witchel, ...

Davis, Justin Brickell, and Matt Taylor have been good friends and colleagues without the good sense to be systems researchers. This thesis would have not have been possible without Jikes RVM. I am...

Transferring instances for model-based reinforcement learning (2008)

Matthew E. Taylor, Nicholas K. Jong, Peter Stone

Abstract. Reinforcement learning agents typically require a significant amount of data before performing well on complex tasks. Transfer learning methods have made progress reducing sample...

UT Austin Villa 2008: Standing On Two Legs (2008)

Todd Hester, Michael Quinlan, Peter Stone

In 2008, UT Austin Villa entered a team in the first Nao competition of the Standard Platform League of the RoboCup competition. The team had previous experience in RoboCup in the Aibo leagues. Using...

Initial Results in RoboCup Soccer (2007)

Gregory Kuhlmann, Peter Stone, Raymond Mooney, Jude Shavlik

We describe our current efforts towards creating a reinforcement learner that learns both from reinforcements provided by its environment and from human-generated advice. Our research involves two...

Autonomous Bidding Agents Edited by (2007)

Peter Stone, Amy Greenwald

This article summarizes the bidding algorithms developed for the on-line Trading Agent Competition held in July, 2000 in Boston. At its heart, the article describes 12 of the 22 agent strategies in...

The RoboCup Synthetic Agent (2007)

Hiroaki Kitano, Manuela Veloso, Hitoshi Matsubara, Millrid Tambe, Ilvia Coradeschi, Itsuki Noda, ...

asadaraech. eng. osaka-u. ac. jp RoboCup Chollenge offers o set of chollenges for intelligent ogent reseorchers using o friendly competition in o dynomic, reol-time, multiogent domoin. While RoboCup...

Team- Part it ioned, Opaque-Transit ion Reinforcement Learning * (2007)

Peter Stone, Manuela Veloso

Abstract. We present a novel multi-agent learning paradigm called team-partitioned, opaque-transition reinforcement learning (TPOT-RL). TPOT-RL introduces the use of action-dependent features to...

Beatin a Defender in Robotic Soccer: Memory-Based Learnin of a Continuous Function (2007)

Peter Stone, Me[nuele Veloso

Learning how to adjust to an opponent's position is critical to the success of having intelligent agents collaborating towards the achievement of specific tasks in unfriendly environments. This...

In RoboCup-97: The First Robot World Cup Soccer Games and Conferences, (2007)

Manuela Veloso, Peter Stone, Kwun Han, Sorin Achim

Abstract. Robotic soccer is a challenging research domain which involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. In this paper, we...

In RoboCup-97: Robot Soccer World Cup [, (2007)

Peter Stone, Manuela Veloso

Abstract. The Soccer Server system provides a rich and cha]]enging multiagent, real-time domain. Agents must accurately perceive and act despite a quickly changing, largely hidden, noisy world. They...

3 1 (2007)

Elizabeth Sklar, Simon Parsons, Peter Stone

Abstract. Since team-based projects have been proven to be an effective pedagogical tool, we have been using RoboCup challenges as the basis for class projects in undergraduate courses. This paper...

Conference submission (2/1/02). Modeling Auction Price Uncertainty Using Boosting-based Conditional Density Estimation (2007)

Robert E. Schapire, Peter Stone, David Mcallester, Michael L. Littman

In complicated, interacting auctions, a fundamental problem is the prediction of prices of goods in the auctions, and more broadly, the modeling of uncertainty regarding these prices. In this paper,...

Conference submission (1/22/02). ATTac-2001: A Learning, Autonomous Bidding Agent (2007)

Peter Stone, Robert E. Schapire, Michael L. Littman, David Mcallester

This paper presents a general approach to building autonomous bidding agents to bid in multiple simultaneous auctions for interacting goods. The core of our approach is learning a model of the...

y (2007)

Peter Stone, Robert E. Schapire, Janos A. Csirik, Michael L. Littman, David Mcallester

Abstract. Auctions are becoming an increasingly popular method for transacting business, especially over the Internet. This paper presents a general approach to building autonomous bidding agents to...

3 (2007)

Peter Stone, Michael L. Littman

Abstract. Auctions are an area of great academic and commercial interest, from tiny auctions for toys on eBay to multi-billion-dollar auctions held by governments for resources or contracts. Although...

Autono.mous nts the nt Competition (2007)

Amy Greenwald, Peter Stone

Designing agents that can bid in online simultaneous auctions is a complex task. The authors describe task-specific details and strategies of agents in a trading agent competition.

Journal of Articial Intelligence Research? (200?)?-? Submitted 6/02; published?/? Scaling Reinforcement Learning toward RoboCup Soccer (2007)

Peter Stone, Richard S. Sutton

RoboCup simulated soccer presents many challenges to reinforcement learning methods, including a large state space, hidden and uncertain state, multiple agents, and long and variable delays in the...

1 (2007)

Janos A. Csirik, Michael L. Littman, Satinder Singh, Peter Stone

Abstract. We introduce FAucS, a software testbed for studying automated agent bidding strategies in simulated auctions, specically the United States FCC wireless frequency spectrum auctions. In...

ATTUnited-2001: Using Heterogeneous Players (2007)

Peter Stone

ATTUnited-2001 is a successor of the CMUnited teams: CMUnited-97, CMUnited98, CMUnited-99, and ATT-CMUnited-2000. It is built mainly upon CMUnited99 [4]. It also incorporates the team action...

The CMUnited-99 Simulator Team (2007)

Peter Stone, Manuela Veloso, Patrick Riley

Abstract. The CMUnited-98 simulator team became the 1998 RoboCup simulator league champion by winning all 8 of its games, outscoring opponents by a total of 66--0. CMUnited-99 builds upon the...

2 (2007)

Peter Stone, Patrick Riley, Manuela Veloso

A common challenge for agents in multiagent systems is trying to predict what other agents are going to do in the future. Such knowledge can help an agent determine which of its current action...

3 1 (2007)

Elizabeth Sklar, Simon Parsons, Peter Stone

Abstract. Since team-based projects have been proven to be an effective pedagogical tool, we have been using RoboCup challenges as the basis for class projects in undergraduate courses. This paper...

Learning to Identify Irrelevant State Variables (2007)

Nicholas K. Jong, Peter Stone

When they are available, safe state abstractions improve the efficiency of reinforcement learning algorithms by allowing an agent to ignore irrelevant distinctions between states while still learning...

Towards employing PSRs in a continuous domain (2007)

Nicholas K. Jong, Peter Stone

Predictive State Representations (PSRs) recently emerged as an alternative framework for reasoning about stochastic environments. However, unlike Markov decision processes, they have not yet been...

Towards Autonomic Computing: Adaptive Network Routing and Scheduling (2007)

Shimon Whiteson And, Shimon Whiteson, Peter Stone

Computer systems are rapidly becoming so complex that maintaining them with human support staffs will be prohibitively expensive and inefficient. In response, visionaries have begun proposing that...

Autonomous Bidding Agents Edited by (2007)

Peter Stone, Amy Greenwald

This article summarizes the bidding algorithms developed for the on-line Trading Agent Competition held in July, 2000 in Boston. At its heart, the article describes 12 of the 22 agent strategies in...

Machine learning for on-line hardware reconfiguration (2007)

Jonathan Wildstrom, Peter Stone, Emmett Witchel, Mike Dahlin

As computer systems continue to increase in complexity, the need for AI-based solutions is becoming more urgent. For example, high-end servers that can be partitioned into logical subsystems and...

A comparison of two approaches for vision and self-localization on a mobile robot (2007)

Daniel Stronger, Peter Stone

Abstract — This paper considers two approaches to the problem of vision and self-localization on a mobile robot. In the first approach, the perceptual processing is primarily bottom-up, with visual...

Machine learning for on-line hardware reconfiguration (2007)

Jonathan Wildstrom, Peter Stone, Emmett Witchel, Mike Dahlin

As computer systems continue to increase in complexity, the need for AI-based solutions is becoming more urgent. For example, high-end servers that can be partitioned into logical subsystems and...

General game learning using knowledge transfer (2007)

Bikramjit Banerjee, Peter Stone

We present a reinforcement learning game player that can interact with a General Game Playing system and transfer knowledge learned in one game to expedite learning in many other games. We use the...

Sharing the road: Autonomous vehicles meet human drivers (2007)

Kurt Dresner, Peter Stone

In modern urban settings, automobile traffic and collisions lead to endless frustration as well as significant loss of life, property, and productivity. Recent advances in artificial intelligence...

Acknowledgments (2007)

Jefferson Provost, Benjamin J. Kuipers, Risto Miikkulainen Supervisor, Raymond Mooney, Bruce Porter, Peter Stone, ...

A couple of years ago someone forwarded me a link to an article interpreting Frodo’s quest in The Lord of the Rings as an allegory for writing and filing a dissertation (Lee, 2005). At the time, I...

The chin pinch: A case study in skill learning on a legged robot (2007)

Peggy Fidelman, Peter Stone

Abstract. When developing skills on a physical robot, it is appealing to turn to modern machine learning methods in order to automate the process. However, when no accurate simulator exists for the...

Color learning on a mobile robot: Towards full autonomy under changing illumination (2007)

Mohan Sridharan, Peter Stone

A central goal of robotics and AI is to be able to deploy an agent to act autonomously in the real world over an extended period of time. It is commonly asserted that in order to do so, the agent...

General game learning using knowledge transfer (2007)

Bikramjit Banerjee, Peter Stone

We present a reinforcement learning game player that can interact with a General Game Playing system and transfer knowledge learned in one game to expedite learning in many other games. We use the...

Color learning on a mobile robot: Towards full autonomy under changing illumination (2007)

Mohan Sridharan, Peter Stone

A central goal of robotics and AI is to be able to deploy an agent to act autonomously in the real world over an extended period of time. It is commonly asserted that in order to do so, the agent...

Color learning on a mobile robot: Towards full autonomy under changing illumination (2007)

Mohan Sridharan, Peter Stone

A central goal of robotics and AI is to be able to deploy an agent to act autonomously in the real world over an extended period of time. It is commonly asserted that in order to do so, the agent...

The UT Austin Villa 3D Simulation Soccer Team 2007 (2007)

Shivaram Kalyanakrishnan, Peter Stone

Abstract. In this paper, we describe the soccer playing agent developed by our team UT Austin Villa to participate in the RoboCup 3D simulation soccer competition held in Atlanta, U.S.A., in July...

Machine learning for on-line hardware reconfiguration (2007)

Jonathan Wildstrom, Peter Stone, Emmett Witchel, Mike Dahlin

As computer systems continue to increase in complexity, the need for AI-based solutions is becoming more urgent. For example, high-end servers that can be partitioned into logical subsystems and...

Model-based exploration in continuous state spaces (2007)

Nicholas K. Jong, Peter Stone

Abstract. Modern reinforcement learning algorithms effectively exploit experience data sampled from an unknown controlled dynamical system to compute a good control policy, but to obtain the...

Batch reinforcement learning in a complex domain (2007)

Shivaram Kalyanakrishnan, Peter Stone

Temporal difference reinforcement learning algorithms are perfectly suited to autonomous agents because they learn directly from an agent’s experience based on sequential actions in the...

Robot Developmental Learning of an Object Ontology Grounded in Sensorimotor Experience (2007)

Joseph Varughese Modayil, Benjamin Kuipers Supervisor, Raymond Mooney, Peter Stone, Brian Stankiewicz, David Kortenkamp, ...

This work would not have been possible without the support of many individuals. My advisor Ben Kuipers has been a source of constant support and stimulation. Without his guidance, my research would...

Sharing the road: Autonomous vehicles meet human drivers (2007)

Kurt Dresner, Peter Stone

In modern urban settings, automobile traffic and collisions lead to endless frustration as well as significant loss of life, property, and productivity. Recent advances in artificial intelligence...

Graph-based domain mapping for transfer learning in general games (2007)

Gregory Kuhlmann, Peter Stone

Abstract. A general game player is an agent capable of taking as input a description of a game’s rules in a formal language and proceeding to play without any subsequent human input. To do well, an...

A comparison of two approaches for vision and self-localization on a mobile robot (2007)

Daniel Stronger, Peter Stone

Abstract — This paper considers two approaches to the problem of vision and self-localization on a mobile robot. In the first approach, the perceptual processing is primarily bottom-up, with visual...

Autonomous learning of stable quadruped locomotion (2007)

Manish Saggar, Nate Kohl, Peter Stone

Abstract. A fast gait is an essential component of any successful team in the RoboCup 4-legged league. However, quickly moving quadruped robots, including those with learned gaits, often move in such...

Cross-domain transfer for reinforcement learning (2007)

Matthew E. Taylor, Peter Stone

A typical goal for transfer learning algorithms is to utilize knowledge gained in a source task to learn a target task faster. Recently introduced transfer methods in reinforcement learning settings...

Cross-domain transfer for reinforcement learning (2007)

Matthew E. Taylor, Peter Stone

A typical goal for transfer learning algorithms is to utilize knowledge gained in a source task to learn a target task faster. Recently introduced transfer methods in reinforcement learning settings...

A comparison of two approaches for vision and self-localization on a mobile robot (2007)

Daniel Stronger, Peter Stone

Abstract — This paper considers two approaches to the problem of vision and self-localization on a mobile robot. In the first approach, the perceptual processing is primarily bottom-up, with visual...

Model-based exploration in continuous state spaces (2007)

Nicholas K. Jong, Peter Stone

Abstract. Modern reinforcement learning algorithms effectively exploit experience data sampled from an unknown controlled dynamical system to compute a good control policy, but to obtain the...

Designing Safe, Profitable Automated Stock Trading Agents Using Evolutionary Algorithms (2006)

Subramanian, Harish, Ramamoorthy, Subramanian, Stone, Peter, Kuipers, Benjamin

Trading rules are widely used by practitioners as an effective means to mechanize aspects of their reasoning about stock price trends. However, due to the simplicity of these rules, each rule is...

Designing safe, profitable automated stock trading agents using evolutionary algorithms (2006)

Harish Subramanian, Subramanian Ramamoorthy, Peter Stone, Benjamin J. Kuipers

Trading rules are widely used by practitioners as an effective means to mechanize aspects of their reasoning about stock price trends. However, due to the simplicity of these rules, each rule is...

Automatic heuristic construction in a complete general game player (2006)

Gregory Kuhlmann, Kurt Dresner, Peter Stone

Computer game players are typically designed to play a single game: today’s best chess-playing programs cannot play checkers, or even tic-tac-toe. General Game Playing is the problem of designing...

Adapting to workload changes through on-the-fly reconfiguration (2006)

Jonathan Wildstrom, Peter Stone, Emmett Witchel, Mike Dahlin

High-end servers that can be partitioned into logical subsystems and repartitioned on the fly are now becoming available. This development raises the possibility of reconfiguring distributed systems...

Adapting to workload changes through on-the-fly reconfiguration (2006)

Peter Stone, Emmett Witchel, Mike Dahlin

Abstract High-end servers that can be partitioned into logical subsystems and repartitioned on the fly are now becomingavailable. This development raises the possibility of reconfiguring distributed...

Value Function Transfer for General Game Playing (2006)

Bikramjit Banerjee, Gregory Kuhlmann, Peter Stone

We present value function transfer techniques for General Game Playing (GGP) by Reinforcement Learning. We focus on 2 player, alternate-move, complete information board games and use the GGP...

Multiagent traffic management: Opportunities for multiagent learning (2006)

Kurt Dresner, Peter Stone

Abstract. Traffic congestion is one of the leading causes of lost productivity and decreased standard of living in urban settings. In previous work published at AAMAS, we have proposed a novel...

Autonomous planned color learning on a mobile robot without labeled data (2006)

Mohan Sridharan, Peter Stone

Color segmentation is a challenging yet integral subtask of mobile robot systems that use visual sensors, especially since they typically have limited computational and memory resources. We present...

From pixels to multi-robot decision-making: A study in uncertainty. Robotics and Autonomous Systems: Special issue on Planning Under Uncertainty in Robotics (2006)

Peter Stone, Mohan Sridharan, Daniel Stronger, Gregory Kuhlmann, Nate Kohl, Peggy Fidelman, ...

Mobile robots must cope with uncertainty from many sources along the path from interpreting raw sensor inputs to behavior selection to execution of the resulting primitive actions. This article...

Adapting to workload changes through on-the-fly reconfiguration (2006)

Jonathan Wildstrom, Peter Stone, Emmett Witchel, Mike Dahlin

High-end servers that can be partitioned into logical subsystems and repartitioned on the fly are now becoming available. This development raises the possibility of reconfiguring distributed systems...

Designing Safe, Profitable Automated Stock Trading (2006)

Agents Using Evolutionary, Harish Subramanian, Subramanian Ramamoorthy, Peter Stone, Benjamin J. Kuipers

Trading rules are widely used by practitioners as an effective means to mechanize aspects of their reasoning about stock price trends. However, due to the simplicity of these rules, each rule is...

Evolutionary function approximation for reinforcement learning (2006)

Shimon Whiteson, Peter Stone, Sven Koenig, Shie Mannor, Georgios Theocharous

Temporal difference methods are theoretically grounded and empirically effective methods for addressing reinforcement learning problems. In most real-world reinforcement learning tasks, TD methods...

Value Function Transfer for General Game Playing (2006)

Bikramjit Banerjee, Gregory Kuhlmann, Peter Stone

We present value function transfer techniques for General Game Playing (GGP) by Reinforcement Learning. We focus on 2 player, alternate-move, complete information board games and use the GGP...

Value-function-based transfer for reinforcement learning using structure mapping (2006)

Yaxin Liu, Peter Stone

Transfer learning concerns applying knowledge learned in one task (the source) to improve learning another related task (the target). In this paper, we use structure mapping, a psychological and...

Keepaway soccer: From machine learning testbed to benchmark (2006)

Peter Stone, Gregory Kuhlmann, Matthew E. Taylor, Yaxin Liu

Abstract. Keepaway soccer has been previously put forth as a testbed for machine learning. Although multiple researchers have used it successfully for machine learning experiments, doing so has...

Adaptive mechanism design: a metalearning approach (2006)

David Pardoe, Peter Stone

Auction mechanism design has traditionally been a largely analytic process, relying on assumptions such as fully rational bidders. In practice, however, bidders often exhibit unknown and variable...

Evolutionary function approximation for reinforcement learning (2006)

Shimon Whiteson, Peter Stone, Georgios Theocharous

Temporal difference methods are theoretically grounded and empirically effective methods for addressing reinforcement learning problems. In most real-world reinforcement learning tasks, TD methods...

Towards autonomous sensor and actuator model induction on a mobile robot (2006)

Daniel Stronger, Peter Stone

1 This article presents a novel methodology for a robot to autonomously induce models of its actions and sensors called asami (Autonomous Sensor and Actuator Model Induction). While previous...

Automatic heuristic construction in a complete general game player (2006)

Gregory Kuhlmann, Kurt Dresner, Peter Stone

Computer game players are typically designed to play a single game: today’s best chess-playing programs cannot play checkers, or even tic-tac-toe. General Game Playing is the problem of designing...

To appear in Adaptive Behavior, 15(1), 2007. Empirical Studies in Action Selection with Reinforcement Learning (2006)

Shimon Whiteson, Matthew E. Taylor, Peter Stone

To excel in challenging tasks, intelligent agents need sophisticated mechanisms for action selection: they need policies that dictate what action to take in each situation. Reinforcement learning...

From pixels to multi-robot decision-making: A study in uncertainty. Robotics and Autonomous Systems: Special issue on Planning Under Uncertainty in Robotics (2006)

Peter Stone, Mohan Sridharan, Daniel Stronger, Gregory Kuhlmann, Nate Kohl, Peggy Fidelman, ...

Mobile robots must cope with uncertainty from many sources along the path from interpreting raw sensor inputs to behavior selection to execution of the resulting primitive actions. This article...

Keepaway soccer: From machine learning testbed to benchmark (2006)

Peter Stone, Gregory Kuhlmann, Matthew E. Taylor, Yaxin Liu

Abstract. Keepaway soccer has been previously put forth as a testbed for machine learning. Although multiple researchers have used it successfully for machine learning experiments, doing so has...

Value Function Transfer for General Game Playing (2006)

Bikramjit Banerjee, Gregory Kuhlmann, Peter Stone

We present value function transfer techniques for General Game Playing (GGP) by Reinforcement Learning. We focus on 2 player, alternate-move, complete information board games and use the GGP...

The UT Austin Villa 2006 RoboCup four-legged team,” The (2006)

Peter Stone, Peggy Fidelman, Nate Kohl, Gregory Kuhlmann, Tekin Meriçli, Mohan Sridharan, ...

The UT Austin Villa Four-Legged Team for RoboCup 2006 was a fourth-time entry in the ongoing series of RoboCup legged league competitions. The team development began in mid-January of 2003 without...

To appear in Adaptive Behavior, 15(1), 2007. Empirical Studies in Action Selection with Reinforcement Learning (2006)

Shimon Whiteson, Matthew E. Taylor, Peter Stone

To excel in challenging tasks, intelligent agents need sophisticated mechanisms for action selection: they need policies that dictate what action to take in each situation. Reinforcement learning...

Evolutionary function approximation for reinforcement learning (2006)

Shimon Whiteson, Peter Stone, Sven Koenig, Shie Mannor, Georgios Theocharous

Temporal difference methods are theoretically grounded and empirically effective methods for addressing reinforcement learning problems. In most real-world reinforcement learning tasks, TD methods...

A multi-robot system for continuous area sweeping tasks (2006)

Mazda Ahmadi, Peter Stone

Abstract — As mobile robots become increasingly autonomous over extended periods of time, opportunities arise for their use on repetitive tasks. We define and implement behaviors for a class of...

Know thine enemy: A champion RoboCup coach agent (2006)

Gregory Kuhlmann, William B. Knox, Peter Stone

In a team-based multiagent system, the ability to construct a model of an opponent team’s joint behavior can be useful for determining an agent’s expected distribution over future world states,...

Know thine enemy: A champion RoboCup coach agent (2006)

Gregory Kuhlmann, William B. Knox, Peter Stone

In a team-based multiagent system, the ability to construct a model of an opponent team’s joint behavior can be useful for determining an agent’s expected distribution over future world states,...

Value-function-based transfer for reinforcement learning using structure mapping (2006)

Yaxin Liu, Peter Stone

Transfer learning concerns applying knowledge learned in one task (the source) to improve learning another related task (the target). In this paper, we use structure mapping, a psychological and...

A multi-robot system for continuous area sweeping tasks (2006)

Mazda Ahmadi, Peter Stone

Abstract — As mobile robots become increasingly autonomous over extended periods of time, opportunities arise for their use on repetitive tasks. We define and implement behaviors for a class of...

Automatic heuristic construction in a complete general game player (2006)

Gregory Kuhlmann, Kurt Dresner, Peter Stone

Computer game players are typically designed to play a single game: today’s best chess-playing programs cannot play checkers, or even tic-tac-toe. General Game Playing is the problem of designing...

Transfer learning for policy search methods (2006)

Matthew E. Taylor, Shimon Whiteson, Peter Stone

An ambitious goal of transfer learning is to learn a task faster after training on a different, but related, task. In this paper we extend a previously successful temporal difference (Sutton &...

TacTex-05: An adaptive agent for TAC SCM (2006)

David Pardoe, Peter Stone, Mark Vanmiddlesworth

Abstract. Supply chains are ubiquitous in the manufacturing of many complex products. Traditionally, supply chains have been created through the interactions of human representatives of the companies...

Research Platform � Sony Aibo (Artificial Intelligence roBOt) (2006)

Nate Kohl, Peter Stone

� To make the robot walk � To make the robot learn to walk � To make the robot learn to walk fast

Model catalyst studies of the strong metal-support interaction: surface structure identified by STM on Pd nanoparticles on TiO2(110) (2005)

Bowker, Michael, Stone, Peter, Morrall, Peter, Smith, Rupert, Bennett, Roger, Perkins, Neil, ...

Model catalysts of Pd nanoparticles and films on TiO2(110) were fabricated by metal vapour deposition (MVD). Molecular beam measurements show that the particles are active for CO adsorption, with a...

Model catalyst studies of the strong metal-support interaction: surface structure identified by STM on Pd nanoparticles on TiO2(110) (2005)

Bowker, Michael, Stone, Peter, Morrall, Peter, Smith, Rupert, Bennett, Roger, Perkins, Neil, ...

Model catalysts of Pd nanoparticles and films on TiO2(110) were fabricated by metal vapour deposition (MVD). Molecular beam measurements show that the particles are active for CO adsorption, with a...

A new model for electric force microscopy and its application for electrostatically generated phase difference in tapping mode AFM / (2005)

Stone, Peter (Peter Robert)

The harmonic force balance method was used to model and simulate electric force microscopy (EFM) and electrostatically generated phase difference in tapping mode AFM (EPTA) measurements. Simulations...

Multiagent Traffic Management: Driver Agent Improvements And A Protocol for Intersection Control (2005)

Kurt Dresner, Peter Stone

Traffic congestion is one of the leading causes of lost productivity and decreased standard of living in urban settings. Recent advances in artificial intelligence suggest vehicle navigation by...

Towards self-configuring hardware for distributed computer systems (2005)

Jonathan Wildstrom, Peter Stone, Emmett Witchel, Raymond J. Mooney, Mike Dahlin

High-end servers that can be partitioned into logical subsystems and repartitioned on the fly are now becoming available. This development raises the possibility of reconfiguring distributed systems...

The ut austin villa 2003 champion simulator coach: A machine learning approach (2005)

Gregory Kuhlmann, Peter Stone, Justin Lallinger

Abstract. The UT Austin Villa 2003 simulated online soccer coach was a first time entry in the RoboCup Coach Competition. In developing the coach, the main research focus was placed on treating...

Evolving keepaway soccer players through task decomposition (2005)

Shimon Whiteson, Nate Kohl, Risto Miikkulainen, Peter Stone

Abstract. In some complex control tasks, learning a direct mapping from an agent's sensors to its actuators is very dicult. For such tasks, decomposing the problem into more manageable...

Simultaneous calibration of action and sensor models on a mobile robot (2005)

Daniel Stronger, Peter Stone

Abstract — This paper presents a technique for the Simultaneous

Practical vision-based Monte Carlo localization on a legged robot (2005)

Mohan Sridharan, Gregory Kuhlmann, Peter Stone

Abstract — Mobile robot localization, the ability of a robot to determine its position and orientation in a global frame of reference, continues to be a major research focus in robotics. In most...

Layered Learning on a Physical Robot (2005)

Peggy Fidelman, Peter Stone

Abstract — Layered learning is a general hierarchical machine learning paradigm that leverages a given task decomposition to learn complex tasks efficiently. Though it has been validated previously...

Evolving keepaway soccer players through task decomposition (2005)

Shimon Whiteson, Nate Kohl, Risto Miikkulainen, Peter Stone

1 Introduction One of the goals of machine learning algorithms is to facilitate the discovery of novel solutions to problems, particularly those that might be unforeseen by human problem-solvers. As...

Towards self-configuring hardware for distributed computer systems (2005)

Jonathan Wildstrom, Peter Stone, Emmett Witchel, Raymond J. Mooney, Mike Dahlin

High-end servers that can be partitioned into logical subsystems and repartitioned on the fly are now becoming available. This development raises the possibility of reconfiguring distributed systems...

The UT Austin Villa 2005 RoboCup four-legged team (2005)

Peter Stone, Kurt Dresner, Peggy Fidelman, Nate Kohl, Gregory Kuhlmann, Mohan Sridharan, ...

The UT Austin Villa Four-Legged Team for RoboCup 2005 was a third-time entry in the ongoing series of RoboCup legged league competitions. The team development began in mid-January of 2003 without any...

Reinforcement learning for RoboCup-soccer keepaway (2005)

Peter Stone, Richard S. Sutton, Gregory Kuhlmann

1 RoboCup simulated soccer presents many challenges to reinforcement learning methods, in-cluding a large state space, hidden and uncertain state, multiple independent agents learning simultaneously,...

Simultaneous calibration of action and sensor models on a mobile robot (2005)

Daniel Stronger, Peter Stone

Abstract — This paper presents a technique for the Simultaneous

A model-based approach to robot joint control (2005)

Daniel Stronger, Peter Stone

Abstract. Despite efforts to design precise motor controllers, robot joints do not always move exactly as desired. This paper introduces a general model-based method for improving the accuracy of...

Towards self-configuring hardware for distributed computer systems (2005)

Jonathan Wildstrom, Peter Stone, Emmett Witchel, Raymond J. Mooney, Mike Dahlin

High-end servers that can be partitioned into logical subsystems and repartitioned on the fly are now becoming available. This development raises the possibility of reconfiguring distributed systems...

Developing Adaptive Auction Mechanisms (2005)

David Pardoe, Peter Stone

Mechanism design has traditionally been a largely analytic process, relying on assumptions such as fully rational bidders. In practice, however, these assumptions may not hold, making bidder behavior...

Function approximation via tile coding: Automating parameter choice (2005)

Er A. Sherstov, Peter Stone

Abstract. Reinforcement learning (RL) is a powerful abstraction of sequential decision making that has an established theoretical foundation and has proven effective in a variety of small, simulated...

A model-based approach to robot joint control (2005)

Daniel Stronger, Peter Stone

Abstract. Despite efforts to design precise motor controllers, robot joints do not always move exactly as desired. This paper introduces a general model-based method for improving the accuracy of...

Three Degrees of Freedom (2005)

Nate Kohl, Peter Stone, Pawel Pytlak, Power Utilization

◮ One of main goals in the field of robotics is to be able to deploy a fully autonomous robot in an unstructured dynamic environment for an extended period of time. ◮ Work is done to improve:

Evolving keepaway soccer players through task decomposition (2005)

Shimon Whiteson, Nate Kohl, Risto Miikkulainen, Peter Stone

Abstract. In some complex control tasks, learning a direct mapping from an agent’s sensors to its actuators is very difficult. For such tasks, decomposing the problem into more manageable...

On Continuous-Action Q-Learning via Tile Coding Function Approximation (2004)

Er A. Sherstov, Peter Stone

Reinforcement learning (RL) is a powerful machine-learning methodology that has an established theoretical foundation and has proven effective in a variety of small, simulated domains. There has been...

Learning ball acquisition on a physical robot (2004)

Peggy Fidelman, Peter Stone

Abstract--- For a robot to learn to improve its performance based entirely on real-world environmental feedback, the robot's behavior specification and learning algorithm must be constructed so...

Three automated stock-trading agents: A comparative study (2004)

Er A. Sherstov, Peter Stone

Abstract. This paper documents the development of three autonomous stocktrading agents within the framework of the Penn Exchange Simulator (PXS), a novel stock-trading simulator that takes advantage...

Towards illumination invariance in the legged league (2004)

Mohan Sridharan, Peter Stone

Abstract. To date, RoboCup games have all been played under constant, bright lighting conditions. However, in order to meet the overall goal of RoboCup, robots will need to be able to seamlessly...

Automated Stock Trading (2004)

Harish K Subramanian, Harish K Subramanian, Peter Stone, Benjamin Kuipers, Joydeep Ghosh, Harish K Subramanian, ...

Acknowledgements I would like to express my deep gratitude to Dr. Peter Stone for his guidance, advice, and encouragement. It has been great fun and a privilege to conduct research under his...

Guiding a reinforcement learner with natural language advice: Initial results in RoboCup soccer (2004)

Gregory Kuhlmann, Peter Stone, Raymond Mooney

We describe our current efforts towards creating a reinforcement learner that learns both from reinforcements provided by its environment and from human-generated advice. Our research involves two...

Machine learning for fast quadrupedal locomotion (2004)

Nate Kohl, Peter Stone

For a robot, the ability to get from one place to another is one of the most basic skills. However, locomotion on legged robots is a challenging multidimensional control problem. This paper presents...

Progress in Learning 3 vs. 2 Keepaway (2004)

Gregory Kuhlmann, Peter Stone

Abstract. Reinforcement learning has been successfully applied to several subtasks in the RoboCup simulated soccer domain. Keepaway is one such task. One notable success in the keepaway domain has...

Progress in Learning 3 vs. 2 Keepaway (2004)

Gregory Kuhlmann, Peter Stone

Abstract. Reinforcement learning has been successfully applied to several subtasks in the RoboCup simulated soccer domain. Keepaway is one such task. One notable success in the keepaway domain has...

Learning ball acquisition on a physical robot (2004)

Peggy Fidelman, Peter Stone

Abstract — For a robot to learn to improve its performance based entirely on real-world environmental feedback, the robot’s behavior specification and learning algorithm must be constructed so as...

Machine learning for fast quadrupedal locomotion (2004)

Nate Kohl, Peter Stone

For a robot, the ability to get from one place to another is one of the most basic skills. However, locomotion on legged robots is a challenging multidimensional control problem. This paper presents...

Two stock-trading agents: Market making and technical analysis (2004)

Yi Feng, Ronggang Yu, Peter Stone

Evolving information technologies have brought computational power and real-time facilities into the stock market. Automated stock trading draws much interest from both the elds of computer science...

Progress in Learning 3 vs. 2 Keepaway (2004)

Gregory Kuhlmann, Peter Stone

Abstract. Reinforcement learning has been successfully applied to several subtasks in the RoboCup simulated soccer domain. Keepaway is one such task. One notable success in the keepaway domain has...

The UT Austin Villa 2003 four-legged team (2004)

Peter Stone, Kurt Dresner, Selim T. Erdogan, Peggy Fidelman, Nicholas K. Jong, Nate Kohl, ...

a new entry in the ongoing series of RoboCup legged league competitions. The team development began in mid-January of 2003, at which time none of the team members had any familiarity with the Aibos....

Progress in Learning 3 vs. 2 Keepaway (2004)

Peter Stone, Richard S. Sutton, Satinder Singh

Abstract. As a sequential decision problem, robotic soccer can bene t from research in reinforcement learning. We introduce the 3 vs. 2 keepaway domain, a subproblem of robotic soccer implemented in...

Progress in Learning 3 vs. 2 Keepaway (2004)

Peter Stone, Richard S. Sutton, Satinder Singh

Abstract. As a sequential decision problem, robotic soccer can bene t from research in reinforcement learning. We introduce the 3 vs. 2 keepaway domain, a subproblem of robotic soccer implemented in...

The UT Austin Villa 2003 Champion Simulator Coach: A Machine Learning Approach (2004)

Gregory Kuhlmann, Peter Stone, Justin Lallinger

The UT Austin Villa 2003 simulated online soccer coach was a rst time entry in the RoboCup Coach Competition. In developing the coach, the main research focus was placed on treating advice-giving as...

Bidding for Customer Orders in TAC SCM (2004)

David Pardoe And, David Pardoe, Peter Stone

Supply chains are a current, challenging problem for agentbased electronic commerce. Motivated by the Trading Agent Competition Supply Chain Management (TAC SCM) scenario, we consider an individual...

Towards Autonomic Computing: Adaptive Job Routing (2004)

And Scheduling Shimon, Shimon Whiteson, Peter Stone

Computer systems are rapidly becoming so complex that maintaining them with human support stas will be prohibitively expensive and inecient. In response, visionaries have begun proposing that...

Guiding a Reinforcement Learner with Natural Language Advice: Initial Results in RoboCup Soccer (2004)

Gregory Kuhlmann, Peter Stone, Raymond Mooney, Jude Shavlik

We describe our current efforts towards creating a reinforcement learner that learns both from reinforcements provided by its environment and from human-generated advice. Our research involves two...

Guiding a Reinforcement Learner with Natural Language Advice: (2004)

Initial Results In, Gregory Kuhlmann, Peter Stone, Raymond Mooney, Jude Shavlik

We describe our current efforts towards creating a reinforcement learner that learns both from reinforcements provided by its environment and from human-generated advice. Our research involves two...

A Model-Based Approach to Robot Joint Control (2004)

Daniel Stronger And, Daniel Stronger, Peter Stone

Despite eorts to design precise motor controllers, robot joints do not always move exactly as desired. This paper introduces a general model-based method for improving the accuracy of joint control.

Policy Gradient Reinforcement Learning for Fast Quadrupedal Locomotion (2004)

Nate Kohl, Peter Stone

This paper presents a machine learning approach to optimizing a quadrupedal trot gait for forward speed. Given a parameterized walk designed for a specific robot, we propose using a form of policy...

Two Stock-Trading Agents: Market Making and Technical Analysis (2004)

Yi Feng, Ronggang Yu, Peter Stone

Evolving information technologies have brought computational power and real-time facilities into the stock market. Automated stock trading draws much interest from both the elds of computer science...

Speeding up Reinforcement Learning with (2004)

Behavior Transfer Matthew, Matthew E. Taylor, Peter Stone

Reinforcement learning (RL) methods (Sutton & Barto 1998) have become popular machine learning techniques in recent years. RL has had some experimental successes and has been shown to exhibit...

Progress in Learning 3 vs. 2 Keepaway (2004)

Gregory Kuhlmann, Peter Stone

Abstract. Reinforcement learning has been successfully applied to several subtasks in the RoboCup simulated soccer domain. Keepaway is one such task. One notable success in the keepaway domain has...

Guiding a reinforcement learner with natural language advice: Initial results in RoboCup soccer (2004)

Gregory Kuhlmann, Peter Stone, Raymond Mooney

We describe our current efforts towards creating a reinforcement learner that learns both from reinforcements provided by its environment and from human-generated advice. Our research involves two...

Towards illumination invariance in the legged league (2004)

Mohan Sridharan, Peter Stone

Abstract. To date, RoboCup games have all been played under constant, bright lighting conditions. However, in order to meet the overall goal of RoboCup, robots will need to be able to seamlessly...

Policy gradient reinforcement learning for fast quadrupedal locomotion (2004)

Nate Kohl, Peter Stone

Abstract — This paper presents a machine learning approach to optimizing a quadrupedal trot gait for forward speed. Given a parameterized walk designed for a specific robot, we propose using a form...

Adaptive job routing and scheduling (2004)

Shimon Whiteson, Peter Stone

Computer systems are rapidly becoming so complex that maintaining them with human support staffs will be prohibitively expensive and inefficient. In response, visionaries have begun proposing that...

Adaptive job routing and scheduling (2004)

Shimon Whiteson, Peter Stone

Computer systems are rapidly becoming so complex that maintaining them with human support staffs will be prohibitively expensive and inefficient. In response, visionaries have begun proposing that...

Machine learning for fast quadrupedal locomotion (2004)

Nate Kohl, Peter Stone

For a robot, the ability to get from one place to another is one of the most basic skills. However, locomotion on legged robots is a challenging multidimensional control problem. This paper presents...

Bidding for customer orders in TAC SCM (2004)

David Pardoe, Peter Stone

Abstract. Supply chains are a current, challenging problem for agentbased electronic commerce. Motivated by the Trading Agent Competition Supply Chain Management (TAC SCM) scenario, we consider an...

Three automated stock-trading agents: A comparative study (2004)

Er A. Sherstov, Peter Stone

Abstract. This paper documents the development of three autonomous stocktrading agents within the framework of the Penn Exchange Simulator (PXS), a novel stock-trading simulator that takes advantage...

Guiding a reinforcement learner with natural language advice: Initial results in RoboCup soccer (2004)

Gregory Kuhlmann, Peter Stone, Raymond Mooney

We describe our current efforts towards creating a reinforcement learner that learns both from reinforcements provided by its environment and from human-generated advice. Our research involves two...

Machine learning for fast quadrupedal locomotion (2004)

Nate Kohl, Peter Stone

For a robot, the ability to get from one place to another is one of the most basic skills. However, locomotion on legged robots is a challenging multidimensional control problem. This paper presents...

Policy gradient reinforcement learning for fast quadrupedal locomotion (2004)

Nate Kohl, Peter Stone

Abstract — This paper presents a machine learning approach to optimizing a quadrupedal trot gait for forward speed. Given a parameterized walk designed for a specific robot, we propose using a form...

Multiagent Traffic Management: A Reservation-Based Intersection Control Mechanism (2004)

Kurt Dresner, Peter Stone

productivity and decreased standard of living in urban settings. Recent advances in artificial intelligence suggest vehicle navigation by autonomous agents will be possible in the near future. In...

Machine Learning for Fast Quadrupedal Locomotion (2004)

Nate Kohl And, Nate Kohl, Peter Stone

For a robot, the ability to get from one place to another is one of the most basic skills. However, locomotion on legged robots is a challenging multidimensional control problem.

TacTex-03: A Supply Chain Management Agent (2004)

David Pardoe And, David Pardoe, Peter Stone

This paper introduces TacTex-03, an agent designed to participate in the Trading Agent Competition Supply Chain Management Scenario (TAC SCM). As speci ed by this scenario, TacTex-03 acts as a...

Towards employing PSRs in a continuous domain (2004)

Nicholas K. Jong, Peter Stone

Predictive State Representations (PSRs) recently emerged as an alternative framework for reasoning about stochastic environments. However, unlike Markov decision processes, they have not yet been...

The 2001 Trading Agent Competition (2003)

Michael P. Wellman, Amy Greenwald, Peter R. Wurman, Peter Stone

The 2001 Trading Agent Competition was the second in a series of events aiming to shed light on research issues in automating trading strategies. Based on a challenging market scenario in the domain...

A polynomial-time Nash equilibrium algorithm for repeated games (2003)

Michael L. Littman, Peter Stone

With the increasing reliance on game theory as a foundation for auctions and electronic commerce, ecient algorithms for computing equilibria in multiplayer general-sum games are of great theoretical...

P.: RoboCup in Higher Education: A preliminary report (2003)

Elizabeth Sklar, Simon Parsons, Peter Stone

Abstract. Since team-based projects have been proven to be an effective pedagogical tool, we have been using RoboCup challenges as the basis for class projects in undergraduate courses. This paper...

Learning predictive state representations (2003)

Satinder Singh, Michael L. Littman, Nicholas K. Jong, David Pardoe, Peter Stone

We introduce the rst algorithm for learning predictive state representations (PSRs), which are a way of representing the state of a controlled dynamical system. The state representation in a PSR is a...

P.: Performance analysis of a counter-intuitive automated stock-trading agent (2003)

Ronggang Yu, Peter Stone

Autonomous trading in the stock market is an area of great interest in both academic and commercial circles. A lot of trading strategies have been proposed and practiced from the perspectives of...

A polynomial-time Nash equilibrium algorithm for repeated games (2003)

Michael L. Littman, Peter Stone

With the increasing reliance on game theory as a foundation for auctions and electronic commerce, e#cient algorithms for computing equilibria in multiplayer general-sum games are of great theoretical...

Dedication To (2003)

Joon Woo Kim, K. Suzanne Barber, Ari Arapostathis, Margarida Jacome, Peter Stone, Elmira Popova, ...

my wife, Kyung, and my daughters, Christine and Erin for their love, support, and encouragement Acknowledgements This dissertation is the product not only of my own thinking and writing but also...

Learning predictive state representations (2003)

Satinder Singh, Michael L. Littman, Nicholas K. Jong, David Pardoe, Peter Stone

We introduce the rst algorithm for learning predictive state representations (PSRs), which are a way of representing the state of a controlled dynamical system. The state representation in a PSR is a...

The Champion UT Austin Villa 2003 Simulator Online Coach Team (2003)

Gregory Kuhlmann, Peter Stone, Justin Lallinger

The UT Austin Villa 2003 simulated online soccer coach was a rst time entry in the RoboCup Coach Competition. In developing the coach, the main research focus was placed on treating advice-giving as...

Learning Predictive State Representations (2003)

Satinder Singh, Michael L. Littman, Peter Stone, Richard Sutton

We introduce the first algorithm for learning predictive state representations.

P.: RoboCup in Higher Education: A preliminary report (2003)

Elizabeth Sklar, Simon Parsons, Peter Stone

Abstract. Since team-based projects have been proven to be an effective pedagogical tool, we have been using RoboCup challenges as the basis for class projects in undergraduate courses. This paper...

Proposed establishment of a Bio-Diesel Production facility (Feasibility) (2002)

Garner, Gary O., Hollingsworth, Peter, Stone, Peter

The outcome of this Report suggests there is strong viability for the establishment of a 60,000 tonne p.a. (raw material input) biodiesel plant.A plant of this size would provide an annual output (at...

Proposed establishment of a Bio-Diesel Production facility (Feasibility) (2002)

Garner, Gary O., Hollingsworth, Peter, Stone, Peter

The outcome of this Report suggests there is strong viability for the establishment of a 60,000 tonne p.a. (raw material input) biodiesel plant.A plant of this size would provide an annual output (at...

Proposed establishment of a Bio-Diesel Production facility (Feasibility) (2002)

Garner, Gary O., Hollingsworth, Peter, Stone, Peter

The outcome of this Report suggests there is strong viability for the establishment of a 60,000 tonne p.a. (raw material input) biodiesel plant.A plant of this size would provide an annual output (at...

Proposed establishment of a Bio-Diesel Production facility (Feasibility) (2002)

Garner, Gary O., Hollingsworth, Peter, Stone, Peter

The outcome of this Report suggests there is strong viability for the establishment of a 60,000 tonne p.a. (raw material input) biodiesel plant.A plant of this size would provide an annual output (at...

Proposed establishment of a Bio-Diesel Production facility (Feasibility) (2002)

Garner, Gary O., Hollingsworth, Peter, Stone, Peter

The outcome of this Report suggests there is strong viability for the establishment of a 60,000 tonne p.a. (raw material input) biodiesel plant.A plant of this size would provide an annual output (at...

Proposed establishment of a Bio-Diesel Production facility (Feasibility) (2002)

Garner, Gary O., Hollingsworth, Peter, Stone, Peter

The outcome of this Report suggests there is strong viability for the establishment of a 60,000 tonne p.a. (raw material input) biodiesel plant.A plant of this size would provide an annual output (at...

Proposed establishment of a Bio-Diesel Production facility (Feasibility) (2002)

Garner, Gary O., Hollingsworth, Peter, Stone, Peter

The outcome of this Report suggests there is strong viability for the establishment of a 60,000 tonne p.a. (raw material input) biodiesel plant.A plant of this size would provide an annual output (at...

Self-enforcing strategic demand reduction (2002)

Peter Stone, János A. Csirik, Michael L. Littman

Abstract. Auctions are an area of great academic and commercial interest, from tiny auctions for toys on eBay to multi-billion-dollar auctions held by governments for resources or contracts. Although...

ATTac-2001: A learning, autonomous bidding agent (2002)

Peter Stone, Robert E. Schapire, János A. Csirik, Michael L. Littman, David Mcallester

Abstract. Auctions are becoming an increasingly popular method for transacting business, especially over the Internet. This paper presents a general approach to building autonomous bidding agents to...

Randomized strategic demand reduction: Getting more by asking for less (2002)

Peter Stone, Janos A. Csirik, Michael L. Littman

Auctions are an area of great academic and commercial interest, from tiny auctions for toys on eBay to multi-billiondollar auctions held by governments for resources or contracts. Although there has...

Keepaway soccer: a machine learning testbed (2002)

Peter Stone, Richard S. Sutton

Abstract. RoboCup simulated soccer presents many challenges to machine learning (ML) methods, including a large state space, hidden and uncertain state, multiple agents, and long and variable delays...

Multiagent competitions and research: Lessons from RoboCup and TAC (2002)

Peter Stone

Abstract. This paper compares and contrasts two recent series of competitions in which multiple agents compete directly against one another: the robot soccer world cup (RoboCup) and the trading agent...

The 2001 trading agent competition (2002)

Michael P. Wellman, Amy Greenwald, Peter Stone, Peter R. Wurman

The 2001 Trading Agent Competition was the second in a series of events aiming to shed light on research issues in automating trading strategies. Based on a challenging market scenario in the domain...

Modeling auction price uncertainty using boosting-based conditional density estimation (2002)

Robert E. Schapire, Peter Stone, David Mcallester, Michael L. Littman

In complicated, interacting auctions, a fundamental problem is the prediction of prices of goods in the auctions, and more broadly, the modeling of uncertainty regarding these prices. In this paper,...

Self-enforcing Strategic Demand Reduction (2002)

Paul Reitsma Peter, Peter Stone, Michael L. Littman

Auctions are an area of great academic and commercial interest, from tiny auctions for toys on eBay to multi-billion-dollar auctions held by governments for resources or contracts. Although there has...

Machine Learning: Proceedings of the Nineteenth International Conference, 2002. Modeling Auction Price Uncertainty (2002)

Robert E. Schapire, Peter Stone, David Mcallester, Michael L. Littman

In complicated, interacting auctions, a fundamental problem is the prediction of prices of goods in the auctions, and more broadly, the modeling of uncertainty regarding these prices. In this paper,...

The 2001 Trading Agent Competition (2002)

Michael P. Wellman, Peter Stone, Amy Greenwald, Peter R. Wurman

The 2001 Trading Agent Competition was the second in a series of events aiming to shed light on research issues in automating trading strategies. Based on a challenging market scenario in the domain...

Modeling auction price uncertainty using boosting-based conditional density estimation (2002)

Robert E. Schapire, Peter Stone, David Mcallester, Michael L. Littman, János A. Csirik

In complicated, interacting auctions, a fundamental problem is the prediction of prices of goods in the auctions, and more broadly, the modeling of uncertainty regarding these prices. In this paper,...

Self-enforcing strategic demand reduction (2002)

Peter Stone, János A. Csirik, Michael L. Littman

Abstract. Auctions are an area of great academic and commercial interest, from tiny auctions for toys on eBay to multi-billion-dollar auctions held by governments for resources or contracts. Although...

Self-enforcing Strategic Demand Reduction (2002)

Paul Reitsma Peter, Peter Stone, János A. Csirik, Michael L. Littman

Auctions are an area of great academic and commercial interest, from tiny auctions for toys on eBay to multi-billion-dollar auctions held by governments for resources or contracts. Although there has...

Modeling auction price uncertainty using boosting-based conditional density estimation (2002)

Robert E. Schapire, Peter Stone, David Mcallester, Michael L. Littman, János A. Csirik

In complicated, interacting auctions, a fundamental problem is the prediction of prices of goods in the auctions, and more broadly, the modeling of uncertainty regarding these prices. In this paper,...

Proposed establishment of a Bio-Diesel Production facility (Feasibility) (2002)

Garner, Gary O., Hollingsworth, Peter, Stone, Peter

The outcome of this Report suggests there is strong viability for the establishment of a 60,000 tonne p.a. (raw material input) biodiesel plant.A plant of this size would provide an annual output (at...

Proposed establishment of a Bio-Diesel Production facility (Feasibility) (2002)

Garner, Gary O., Hollingsworth, Peter, Stone, Peter

The outcome of this Report suggests there is strong viability for the establishment of a 60,000 tonne p.a. (raw material input) biodiesel plant.A plant of this size would provide an annual output (at...

A social reinforcement learning agent (2001)

Charles Lee Isbell, R. Shelton, Michael Kearns, Satinder Singh, Peter Stone

software agent that resides in the well-known online chat community LambdaMOO. Our initial work on Cobot (Isbell et al., 2000) provided him with the ability to collect social statistics and report...

FAucS: An FCC spectrum auction simulator for autonomous bidding agents (2001)

János A. Csirik, Michael L. Littman, Satinder Singh, Peter Stone

Abstract. We introduce FAucS, a software testbed for studying automated agent bidding strategies in simulated auctions, specifically the United States FCC wireless frequency spectrum auctions. In...

Autonomous Bidding Agents (2001)

Peter Stone, Amy Greenwald

This article summarizes the bidding algorithms developed for the on-line Trading Agent Competition held in July, 2000 in Boston. At its heart, the article describes 12 of the 22 agent strategies in...

A social reinforcement learning agent (2001)

Charles Lee Isbell, R. Shelton, Michael Kearns, Satinder Singh, Peter Stone

We report on our reinforcement learning work on Cobot, a software agent that resides in the well-known online chat community LambdaMOO. Our initial work on Cobot (Isbell et al., 2000) provided him...

ATTac-2000: An adaptive autonomous bidding agent (2001)

Peter Stone, Michael L. Littman

The First Trading Agent Competition (TAC) was held from June 22nd to July 8th, 2000. TAC was designed to create a benchmark problem in the complex domain of emarketplaces and to motivate researchers...

Cobot: A social reinforcement learning agent (2001)

Charles Lee Isbell, R. Shelton, Michael Kearns, Satinder Singh, Peter Stone

We report on the use of reinforcement learning with Cobot, a software agent residing in the well-known online community LambdaMOO. Our initial work on Cobot (Isbell et al.2000) provided him with the...

Implicit negotiation in repeated games (2001)

Michael L. Littman, Peter Stone

Abstract. In business-related interactions such as the on-going highstakes FCC spectrum auctions, explicit communication among participants is regarded as collusion, and is therefore illegal. In this...

Leading best-response strategies in repeated games (2001)

Michael L. Littman, Peter Stone

In repeated general-sum games, an agent using a \best response " strategy maximizes its own payo assuming its behavior has no eect on its opponent. This notion of best response requires some...

ATTac-2000: An adaptive autonomous bidding agent (2001)

Peter Stone, Michael L. Littman

The First Trading Agent Competition (TAC) was held from June 22nd to July 8th, 2000. TAC was designed to create a benchmark problem in the complex domain of emarketplaces and to motivate researchers...

Cobot: A social reinforcement learning agent (2001)

Charles Lee Isbell, R. Shelton, Michael Kearns, Satinder Singh, Peter Stone

We report on the use of reinforcement learning with Cobot, a software agent residing in the wellknown online community LambdaMOO. Our initial work on Cobot (Isbell et al.2000) provided him with the...

FAucS: An FCC spectrum auction simulator for autonomous bidding agents (2001)

Michael L. Littman, Satinder Singh, Peter Stone

We introduce FAucS, a software testbed for studying automated agent bidding strategies in simulated auctions, specifically the United States FCC wireless frequency spectrum auctions. In addition to...

ATTac-2000: An adaptive autonomous bidding agent (2001)

Peter Stone, Michael L. Littman

The First Trading Agent Competition (TAC) was held from June 22nd to July 8th, 2000. TAC was designed to create a benchmark problem in the complex domain of emarketplaces and to motivate researchers...

An architecture for action selection in robotic soccer (2001)

Peter Stone, David Mcallester

CMUnited-99 was the 1999 RoboCup robotic soccer simulator league champion. In the RoboCup-2000 competition, CMUnited-99 was entered again and despite being publicly available for the entire year, it...

Scaling reinforcement learning toward Robocup soccer (2001)

Peter Stone, Richard S. Sutton, Gregory Kuhlmann

Editor: ed RoboCup simulated soccer presents many challenges to reinforcement learning methods, including a large state space, hidden and uncertain state, multiple agents, and long and variable...

Layered Disclosure: Revealing Agents' Internals (2001)

Patrick Riley, Peter Stone, Manuela Veloso

A perennial challenge in creating and using complex autonomous agents is following their choices of actions as the world changes dynamically and understanding why they act as they do. This paper...

An architecture for action selection in robotic soccer (2001)

Peter Stone, David Mcallester

content areas: multi-agent teams, coordinating multiple agents,action selection and planning, real-time performance

Cobot: A social reinforcement learning agent (2001)

Charles Lee Isbell, R. Shelton, Michael Kearns, Satinder Singh, Peter Stone

We report on the use of reinforcement learning with Cobot, a software agent residing in the well-known online community LambdaMOO. Our initial work on Cobot (Isbell et al.2000) provided him with the...

ATTac-2000: An adaptive autonomous bidding agent (2001)

Peter Stone, Michael L. Littman, Satinder Singh, Michael Kearns

The First Trading Agent Competition (TAC) was held from June 22nd to July 8th, 2000. TAC was designed to create a benchmark problem in the complex domain of emarketplaces and to motivate researchers...

An architecture for action selection in robotic soccer (2001)

Peter Stone, David Mcallester

ABSTRACT CMUnited-99 was the 1999 RoboCup robotic soccer simulator league champion. In the RoboCup-2000 competition, CMUnited-99 was entered again and despite being publicly available for the entire...

Scaling reinforcement learning toward Robocup soccer (2001)

Peter Stone, Richard S. Sutton

RoboCup simulated soccer presents many challenges to reinforcement learning methods, including a large state space, hidden and uncertain state, multiple agents, and long and variable delays in the e...

Keeping the ball from CMUnited-99 (2001)

David Mcallester, Peter Stone

Abstract. This paper presents preliminary results achieved during our current development of a team for simulated robotic soccer in the RoboCup soccer server [2]. We have constructed a team that...

Scaling reinforcement learning toward Robocup soccer (2001)

Peter Stone, Richard S. Sutton

RoboCup simulated soccer presents many challenges to reinforcement learning methods, including a large state space, hidden and uncertain state, multiple agents, and long and variable delays in the...

Autonomous bidding agents in the Trading Agent Competition (2001)

Amy Greenwald, Peter Stone

Designing agents that can bid in online simultaneous auctions is a complex task.The authors describe task-specific details and strategies of agents in a trading agent competition. Anatural offshoot...

A social reinforcement learning agent (2001)

Charles Lee Isbell, R. Shelton, Michael Kearns, Satinder Singh, Peter Stone

software agent that resides in the well-known online chat community LambdaMOO. Our initial work on Cobot (Isbell et al., 2000) provided him with the ability to collect social statistics and report...

A social reinforcement learning agent (2001)

Charles Lee Isbell, R. Shelton, Michael Kearns, Satinder Singh, Peter Stone

We report on our reinforcement learning work on Cobot, a software agent that resides in the well-known online chat community LambdaMOO. Our initial work on Cobot (Isbell et al., 2000) provided him...

Cobot: A social reinforcement learning agent (2001)

Charles Lee Isbell, R. Shelton, Michael Kearns, Satinder Singh, Peter Stone

We report on the use of reinforcement learning with Cobot, a software agent residing in the wellknown online community LambdaMOO. Our initial work on Cobot (Isbell et al.2000) provided him with the...

Layered disclosure: Revealing agents’ internals (2000)

Patrick Riley, Peter Stone, Manuela Veloso

Abstract. A perennial challenge in creating and using complex autonomous agents is following their choices of actions as the world changes dynamically and understanding why they act as they do. This...

Defining and using ideal teammate and opponent agent models (2000)

Peter Stone

A common challenge for agents in multiagent systems is trying to predict what other agents are going to do in the future. Such knowledge can help an agent determine which of its current action...

Multiagent systems: A survey from a machine learning perspective (2000)

Peter Stone, Manuela Veloso

Distributed Artificial Intelligence (DAI) has existed as a subfield of AI for less than two decades. DAI is concerned with systems that consist of multiple independent entities that interact in a...

Layered learning (2000)

Shimon Whiteson, Peter Stone

Hierarchies are powerful tools for decomposing complex control tasks into manageable subtasks. Several hierarchical approaches have been proposed for creating agents that can execute these tasks....

CMUnited-98: RoboCup-98 small-robot world champion team (2000)

Manuela Veloso, Michael Bowling, Sorin Achim, Kwun Han, Peter Stone

The CMUnited small-robot team became the 1998 RoboCup small-robot league champion, repeating its 1997 victory. CMUnited-98 built upon the success of CMUnited-97, and involved a number of...

Layered learning (2000)

Peter Stone, Manuela Veloso

This paper presents layered learning, a hierarchical machine learning paradigm. Layered learning applies to tasks for which learning a direct mapping from inputs to outputs is intractable with...

Layered Disclosure: Revealing Agents' Internals (2000)

Patrick Riley Peter, Peter Stone, Manuela Veloso

A perennial challenge in creating and using complex autonomous agents is following their choices of actions as the world changes dynamically and understanding why they act as they do. This paper...

Defining and Using Ideal Teammate and Opponent Agent Models (2000)

Peter Stone, Patrick Riley, Manuela Veloso

A common challenge for agents in multiagent systems is trying to predict what other agents are going to do in the future. Such knowledge can help an agent determine which of its current action...

Layered Learning (2000)

Peter Stone, Manuela Veloso

This paper presents "layered learning," a hierarchical machine learning paradigm. Layered learning applies to tasks for which learning a direct mapping from inputs to outputs is in...

Defining and using ideal teammate and opponent agent models (2000)

Peter Stone

A common challenge for agents in multiagent systems is trying to predict what other agents are going to do in the future. Such knowledge can help an agent determine which of its current action...

TPOT-RL applied to network routing (2000)

Peter Stone

Team-partitioned, opaque-transition reinforcement learning (TPOT-RL) is a distributed reinforcement learning technique that allows a team of independent agents to learn a collaborative task. TPOT-RL...

Layered disclosure: Revealing agents’ internals (2000)

Patrick Riley, Peter Stone, Ý Manuela Veloso

Abstract. A perennial challenge in creating and using complex autonomous agents is following their choices of actions as the world changes dynamically and understanding why they act as they do. This...

Defining and Using Ideal Teammate and Opponent Agent Models: A Case Study in Robotic Soccer (2000)

Peter Stone, Patrick Riley, Manuela Veloso

this paper, we introduce "ideal-model-based behavior outcome prediction" (IMBBOP). This technique predicts an agent's future actions in relation to the optimal behavior in its given...

TPOT-RL applied to network routing (2000)

Peter Stone

Team-partitioned, opaque-transition reinforcement learning (TPOT-RL) is a distributed reinforcement learning technique that allows a team of independent agents to learn a collaborative task. TPOT-RL...

The CMUnited-98 champion small robot team (1999)

Manuela Veloso, Michael Bowling, Sorin Achim, Kwun Han, Peter Stone

Abstract. In this chapter, we present the main research contributions of our champion CMUnited-98 small robot team. The team is a multiagent robotic system with global perception, and distributed...

Anticipation as a key for collaboration in a team of agents: A case study in robotic soccer (1999)

Manuela Veloso, Peter Stone, Michael Bowling

We investigate teams of complete autonomous agents that can collaborate towards achieving precise objectives in an adversarial dynamic environment. We have pursued this work in the context of robotic...

Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork (1999)

Peter Stone, Manuela Veloso

Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this article, we introduce periodic team...

Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork (1999)

Peter Stone, Manuela Veloso

Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this article, we introduce periodic team...

The CMUnited-98 champion small robot team (1999)

Manuela Veloso, Michael Bowling, Peter Stone

Robotic soccer presents a large spectrum of challenging research opportunities. In this article, we present the main research and technical contributions of our champion CMUnited-98 small robot team....

Task decomposition and dynamic role assignment for real-time strategic teamwork (1999)

Peter Stone, Manuela Veloso

Abstract. Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this paper, we introduce periodic team...

Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork (1999)

Peter Stone, Manuela Veloso

Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this article, we introduce periodic team...

Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork (1999)

Peter Stone, Manuela Veloso

Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this article, we introduce periodic team...

Layered Extrospection: Why is the agent doing what it’s doing (1999)

Peter Stone, Patrick Riley, Manuela Veloso

A perennial challenge in creating and using complex autonomous agents is following their choice of actions as the world changes dynamically and understanding why they act as they do. This paper...

Anticipation as a key for collaboration in a team of agents: A case study in robotic soccer (1999)

Manuela Veloso, Peter Stone, Michael Bowling

We investigate teams of complete autonomous agents that can collaborate towards achieving precise objectives in an adversarial dynamic environment. We have pursued this work in the context of robotic...

The CMUnited-99 Champion Simulator Team (1999)

Peter Stone, Patrick Riley, Manuela Veloso

The CMUnited-99 simulator team became the 1999 RoboCup simulator league champion by winning all 8 of its games, outscoring opponents by a combined score of 110--0. CMUnited-99 builds upon the...

CMUnited-98: RoboCup-98 Small-Robot World Champion Team (1999)

Manuela Veloso, Michael Bowling, Sorin Achim, Kwun Han, Peter Stone

The CMUnited small-robot team became the 1998 RoboCup small-robot league champion, repeating its 1997 victory. CMUnited-98 built upon the success of CMUnited-97, and involved a number of...

CMUnited-98: RoboCup-98 Simulator World Champion Team (1999)

Peter Stone, Manuela Veloso, Patrick Riley

The CMUnited-98 simulator team became the 1998 RoboCup simulator league champion by winning all 8 of its games, outscoring opponents by a total of 66--0. CMUnited-98 builds upon the successful...

Soccerserver Manual Ver. 5 Rev. 00 beta (for Soccerserver Ver.5.00 and later) (1999)

Ver Rev Beta, Klaus Dorer, Fredrik Heintz, Kostas Kostiadis, Johan Kummeneje, Helmut Myritz, ...

Contents 1 Introduction 3 1.1 History . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.1.1 History of the Soccerserver . . . . . . . . . . . . ....

The CMUnited-99 Champion Simulator Team (1999)

Peter Stone, Patrick Riley, Manuela Veloso

. The CMUnited-99 simulator team became the 1999 RoboCup simulator league champion by winning all 8 of its games, outscoring opponents by a combined score of 110--0. CMUnited-99 builds upon the...

The CMUnited-98 Champion Simulator Team (1999)

Peter Stone, Manuela Veloso, Patrick Riley

. The CMUnited-98 simulator team became the 1998 RoboCup simulator league champion by winning all 8 of its games, outscoring opponents by a total of 66--0. CMUnited-98 builds upon the successful...

Team-Partitioned, Opaque-Transition Reinforcement Learning (1999)

Peter Stone, Manuela Veloso

. We present a novel multi-agent learning paradigm called team-partitioned, opaque-transition reinforcement learning (TPOT-RL). TPOT-RL introduces the use of action-dependent features to generalize...

The CMUnited-98 Champion Simulator Team (1999)

Peter Stone, Manuela Veloso, Patrick Riley

. The CMUnited-98 simulator team became the 1998 RoboCup simulator league champion by winning all 8 of its games, outscoring opponents by a total of 66--0. CMUnited-98 builds upon the successful...

The CMUnited-98 Champion Small-Robot Team (1999)

Manuela Veloso, Michael Bowling, Sorin Achim, Kwun Han, Peter Stone

. In this chapter, we present the main research contributions of our champion CMUnited-98 small robot team. The team is a multiagent robotic system with global perception, and distributed cognition...

The CMUnited-98 champion simulator team (1999)

Peter Stone, Manuela Veloso, Patrick Riley, H. Kitano

Springer Verlag, Berlin, 1999. Abstract. The CMUnited-98 simulator team became the 1998 RoboCup simulator league champion by winning all 8 of its games, outscoring opponents by a total of 66{0....

The CMUnited-98 champion small robot team (1999)

Manuela Veloso, Michael Bowling, Sorin Achim, Kwun Han, Peter Stone

Abstract. In this chapter, we present the main research contributions of our champion CMUnited-98 small robot team. The team is a multiagent robotic system with global perception, and distributed...

CMUnited-98: Robocup-98 simulator world champion team (1999)

Peter Stone, Manuela Veloso, Patrick Riley

The CMUnited-98 simulator team became the 1998 RoboCup simulator league champion by winning all 8 of its games, outscoring opponents by a total of 66–0. CMUnited-98 builds upon the successful...

Task decomposition and dynamic role assignment for real-time strategic teamwork (1999)

Peter Stone, Manuela Veloso

Abstract. Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this paper, we introduce periodic team...

The CMUnited-98 champion small robot team (1999)

Manuela Veloso, Michael Bowling, Peter Stone

Robotic soccer presents a large spectrum of challenging research opportunities. In this article, we present the main research and technical contributions of our champion CMUnited-98 small robot team....

Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork (1999)

Peter Stone, Manuela Veloso

Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this article, we introduce periodic team...

Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork (1999)

Peter Stone, Manuela Veloso

Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this article, we introduce periodic team...

The CMUnited-98 champion simulator team (1999)

Peter Stone, Patrick Riley, Manuela Veloso

simulator league champion by winning all 8 of its games, outscoring opponents by a combined score of 110{0. CMUnited-99 builds upon the successful CMUnited-98 implementation, but also improves upon...

The CMUnited-98 champion simulator team (1999)

Peter Stone, Patrick Riley, Manuela Veloso

simulator league champion by winning all 8 of its games, outscoring opponents by a combined score of 110{0. CMUnited-99 builds upon the successful CMUnited-98 implementation, but also improves upon...

Team-partitioned, opaque-transition reinforcement learning (1999)

Peter Stone, Manuela Veloso

In this paper, we present a novel multi-agent learning paradigm called team-partitioned, opaque-transition reinforcement learning (TPOT-RL). TPOT-RL introduces the concept of using action-dependent...

Beating a Defender in Robotic Soccer: Memory-Based Learning of a Continuous Function, (1998)

Stone, Peter, Veloso, Manuela

Learning how to adjust to an opponent's position is critical to the success of having intelligent agents collaborating towards the achievement of specific tasks in unfriendly environments. This paper...

Multiagent Systems: A Survey from a Machine Learning Perspective (1998)

Stone, Peter, Veloso, Manuela

Distributed Artificial Intelligence (DAI) has existed as a subfield of AI for less than two decades. DAI is concerned with systems that consist of multiple independent entities that interact in a...

Towards collaborative and adversarial learning: A case study in robotic soccer (1998)

Peter Stone, Manuela Veloso

Soccer is a rich domain for the study of multiagent learning issues. Not only must the players learn low-level skills, but they must also learn to work together and to adapt to the behaviors of...

A layered approach to learning client behaviors in the robocup soccer server (1998)

Peter Stone, Manuela Veloso

In the past few years, Multiagent Systems (MAS) has emerged as an active subfield of Artificial Intelligence (AI). Because of the inherent complexity of MAS, there is much interest in using Machine...

Communication in domains with unreliable, single-channel, low-bandwidth communication (1998)

Peter Stone, Manuela Veloso

In most multiagent systems with communicating agents, the agents have the luxury of using reliable, multi-step negotiation protocols. They can do so primarily when communication is reliable and the...

Communication in domains with unreliable, single-channel, low-bandwidth communication (1998)

Peter Stone, Manuela Veloso

Abstract. In most multiagent systems with communicating agents, the agents have the luxury of using reliable, multi-step negotiation protocols. They can do so primarily when communication is reliable...

Using decision tree confidence factors for multiagent control (1998)

Peter Stone, Manuela Veloso

Abstract. Although Decision Trees are widely used for classification tasks, they are typically not used for agent control. This paper presents a novel technique for agent control in a complex...

Anticipation: A Key for Collaboration in a Team of Agents (1998)

Manuela Veloso, Peter Stone, Michael Bowling

We investigate teams of complete autonomous agents that can collaborate towards achieving precise objectives in an adversarial dynamic environment. We have pursued this work in the context of robotic...

Towards collaborative and adversarial learning: A case study in robotic soccer (1998)

Peter Stone, Manuela Veloso

Soccer is a rich domain for the study of multiagent learning issues. Not only must the players learn low-level skills, but they must also learn to work together and to adapt to the behaviors of...

The cmunited-97 robotic soccer team: Perception and multiagent control (1998)

Manuela Veloso, Peter Stone, Kwun Han

Submitted to Autonomous Agents ’98, October 1997 Robotic soccer is a challenging research domain which involves multiple agents that need to collaborate in an adversarial environment to achieve...

CMUnited-97: RoboCup-97 small-robot world champion team (1998)

Manuela Veloso, Peter Stone, Kwun Han

Robotic soccer is a challenging research domain which involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. In this paper, we describe...

CMUnited-97: RoboCup-97 small-robot world champion team (1998)

Manuela Veloso, Peter Stone, Kwun Han, Sorin Achim

Robotic soccer is a challenging research domain which involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. In this paper, we describe...

CMUnited: A team of robotic soccer agents collaborating in an adversarial environment (1998)

Manuela Veloso, Peter Stone, Kwun Han, Sorin Achim

Robotic soccer involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. In this paper, we describe the robotic agents and architecture that we...

Anticipation: A Key for Collaboration in a Team of Agents (1998)

Manuela Veloso, Peter Stone, Michael Bowling

We investigate teams of complete autonomous agents that can collaborate towards achieving precise objectives in an adversarial dynamic environment. We have pursued this work in the context of robotic...

Towards collaborative and adversarial learning: A case study in robotic soccer (1998)

Peter Stone, Manuela Veloso

Soccer is a rich domain for the study of multiagent learning issues. Not only must the players learn low-level skills, but they must also learn to work together and to adapt to the behaviors of...

The CMUnited-97 Small Robot Team (1998)

Manuela Veloso, Peter Stone, Kwun Han, Sorin Achim

. Robotic soccer is a challenging research domain which involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. In this paper, we describe...

The CMUnited-97 Robotic Soccer Team: Perception and Multiagent Control (1998)

Manuela Veloso, Peter Stone, Kwun Han

Robotic soccer is a challenging research domain which involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. In this paper, we describe...

Using Decision Tree Confidence Factors for Multiagent Control (1998)

Peter Stone, Manuela Veloso

Although Decision Trees are widely used for classification tasks, they are typically not used for agent control. This paper presents a novel technique for agent control in a complex multiagent domain...

The RoboCup Physical Agent Challenge: Phase I (1998)

Minoru Asada, Peter Stone, Hiroaki Kitano, Barry Werger, Yasuo Kuniyoshi, Alexis Drogoul, ...

Traditional AI research has not given due attention to the important role that physical bodies play for agents as their interactions produce complex emergent behaviors to achieve goals in the dynamic...

Task Decomposition, Dynamic Role Assignment, and Low-Bandwidth Communication for Real-Time Strategic Teamwork (1998)

Peter Stone, Manuela Veloso

Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this article, we introduce periodic team...

A Layered Approach to Learning Client Behaviors in the RoboCup Soccer Server (1998)

Peter Stone Manuela, Peter Stone, Manuela Veloso

In the past few years, Multiagent Systems (MAS) has emerged as an active subfield of Artificial Intelligence (AI). Because of the inherent complexity of MAS, there is much interest in using Machine...

Communication in Domains with Unreliable, Single-Channel, Low-Bandwidth Communication (1998)

Peter Stone, Manuela Veloso

In most multiagent systems with communicating agents, the agents have the luxury of using reliable, multi-step negotiation protocols. They can do so primarily when communication is reliable and the...

Task Decomposition and Dynamic Role Assignment for Real-Time Strategic Teamwork (1998)

Peter Stone, Manuela Veloso

. Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this paper, we introduce periodic team...

A Layered Approach to Learning Client Behaviors in the RoboCup Soccer Server (1998)

Peter Stone, Manuela Veloso

In the past few years, Multiagent Systems (MAS) has emerged as an active subfield of Artificial Intelligence (AI). Because of the inherent complexity of MAS, there is much interest in using Machine...

Task Decomposition and Dynamic Role Assignment for Real-Time Strategic Teamwork (1998)

Peter Stone, Manuela Veloso

Multiagent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this paper, we introduce periodic team...

Using Decision Tree Confidence Factors for Multiagent Control (1998)

Peter Stone, Manuela Veloso

. Although Decision Trees are widely used for classification tasks, they are typically not used for agent control. This paper presents a novel technique for agent control in a complex multiagent...

Task Decomposition, Dynamic Role Assignment, and Low-Bandwidth Communication for Real-Time Strategic Teamwork (1998)

Peter Stone, Manuela Veloso

Multi-agent domains consisting of teams of agents that need to collaborate in an adversarial environment offer challenging research opportunities. In this article, we introduce periodic team...

Individual and Collaborative Behaviors in a Team of Homogeneous Robotic Soccer Agents (1998)

Manuela Veloso, Peter Stone

Robotic soccer is a new challenging multi-agentdomain, in which agents need to collaborate in an adversarial environment to achieve specific objectives. In this paper, we describe CMUnited-97, our...

The CMUnited-97 Simulator Team (1998)

Peter Stone, Manuela Veloso

. The Soccer Server system provides a rich and challenging multiagent, real-time domain. Agents must accurately perceive and act despite a quickly changing, largely hidden, noisy world. They must...

Communication in Domains with Unreliable, Single-Channel, Low-Bandwidth Communication (1998)

Peter Stone, Manuela Veloso

. In most multiagent systems with communicating agents, the agents have the luxury of using reliable, multi-step negotiation protocols. They can do so primarily when communication is reliable and the...

CMUnited-97: RoboCup-97 Small-Robot World Champion Team (1998)

Manuela Veloso, Peter Stone, Kwun Han

Robotic soccer is a challenging research domain which involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. In this paper, we describe...

Prediction, Behaviors, and Collaboration in a Team of Robotic Soccer Agents (1998)

Manuela Veloso, Peter Stone, Kwun Han, Sorin Achim

Robotic soccer is a challenging research domain which involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. In this paper, we describe...

The CMUnited-97 Small Robot Team (1998)

Manuela Veloso, Peter Stone, Kwun Han, Sorin Achim

. Robotic soccer is a challenging research domain which involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. In this paper, we describe...

Team-Partitioned, Opaque-Transition Reinforcement Learning (1998)

Peter Stone, Manuela Veloso

In this paper, we present a novel multi-agent learning paradigm called team-partitioned, opaque-transition reinforcement learning (TPOT-RL). TPOT-RL introduces the concept of using action-dependent...

The CMUnited-97 Robotic Soccer Team: Perception and Multiagent Control (1998)

Manuela Veloso, Peter Stone, Kwun Han

Robotic soccer is a challenging research domain which involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. In this paper, we describe...

A Layered Approach to Learning Client Behaviors in the RoboCup Soccer Server (1998)

Peter Stone, Manuela Veloso

In the past few years, Multiagent Systems (MAS) has emerged as an active subfield of Artificial Intelligence (AI). Because of the inherent complexity of MAS, there is much interest in using Machine...

Using decision tree confidence factors for multiagent control (1998)

Peter Stone, Manuela Veloso

Although Decision Trees are widely used for classification tasks, they are typically not used for agent control. This paper presents anovel technique for agent control in a complex multiagent domain...

Anticipation: A Key for Collaboration in a Team of Agents (1998)

Manuela Veloso, Peter Stone, Michael Bowling

We investigate teams of complete autonomous agents that can collaborate towards achieving precise objectives in an adversarial dynamic environment. We have pursued this work in the context of robotic...

Layered Learning in Multi-Agent Systems (1998)

Peter Stone, Herbert A. Simon

search, or the U.S. Government. Keywords: Multi-agent systems, machine learning, multi-agent learning, control learning, hierarchical learning, reinforcement learning, decision tree learning, neural...

Communication in domains with unreliable, single-channel, low-bandwidth communication (1998)

Peter Stone, Manuela Veloso

In most multiagent systems with communicating agents, the agents have the luxury of using reliable, multi-step negotiation protocols. They can do so primarily when communication is reliable and the...

The CMUnited-97 small-robot team (1998)

Manuela Veloso, Peter Stone, Kwun Han, Sorin Achim

Abstract. Robotic soccer is a challenging research domain which involves multiple agents that need to collaborate in an adversarial environment toachieve speci c objectives. In this paper, we...

The CMUnited-97 simulator team (1998)

Peter Stone, Manuela Veloso

Abstract. The Soccer Server system provides a rich and challenging multiagent, real-time domain. Agents must accurately perceive and act despite a quickly changing, largely hidden, noisy world. They...

Anticipation: A Key for Collaboration in a Team of Agents (1998)

Manuela Veloso, Peter Stone, Michael Bowling

We investigate teams of complete autonomous agents that can collaborate towards achieving precise objectives in an adversarial dynamic environment. We have pursued this work in the context of robotic...

A layered approach to learning client behaviors in the robocup soccer server (1998)

Peter Stone, Manuela Veloso

In the past few years, Multiagent Systems (MAS) has emerged as an active subfield of Artificial Intelligence (AI). Because of the inherent complexity of MAS, there is much interest in using Machine...

Towards Collaborative and Adversarial Learning: A Case Study in Robotic Soccer (1997)

Peter Stone, Manuela Veloso

Soccer is a rich domain for the study of multiagent learning issues. Not only must the players learn low-level skills, but they must also learn to work together and to adapt to the behaviors of...

Multiagent Systems: A Survey from a Machine Learning Perspective (1997)

Peter Stone, Manuela Veloso

Distributed Artificial Intelligence (DAI) has existed as a subfield of AI for less than two decades. DAI is concerned with systems that consist of multiple independent entities that interact in a...

The RoboCup Synthetic Agent Challenge 97 (1997)

Hiroaki Kitano, Milind Tambe, Peter Stone, Manuela Veloso, Silvia Coradeschi, Eiichi Osawa, ...

RoboCup Challenge offers a set of challenges for intelligent agent researchers using a friendly competition in a dynamic, real-time, multiagent domain. While RoboCup in general envisions longer range...

Multiagent Systems: A Survey from a Machine Learning Perspective (1997)

Peter Stone, Manuela Veloso

Distributed Artificial Intelligence (DAI) has existed as a subfield of AI for less than two decades. DAI is concerned with systems that consist of multiple independent entities that interact in a...

Towards Collaborative and Adversarial Learning: A Case Study in Robotic Soccer (1997)

Peter Stone, Manuela Veloso

Soccer is a rich domain for the study of multi-agent learning issues. Not only must the players learn to adapt to the behavior of different opponents, but they must learn to work together. We are...

The RoboCup Synthetic Agent Challenge 97 (1997)

Hiroaki Kitano, Milind Tambe, Peter Stone, Manuela Veloso, Silvia Coradeschi, Eiichi Osawa, ...

RoboCup Challenge offers a set of challenges for intelligent agent researchers using a friendly competition in a dynamic, real-time, multiagent domain. While RoboCup in general envisions longer range...

Towards Collaborative and Adversarial Learning: A Case Study in Robotic Soccer (1997)

Peter Stone, Manuela Veloso

Soccer is a rich domain for the study of multiagent learning issues. Not only must the players learn low-level skills, but they must also learn to work together and to adapt to the behaviors of...

Multiagent Systems: A Survey from a Machine Learning Perspective (1997)

Peter Stone, Manuela Veloso

Distributed Artificial Intelligence (DAI) has existed as a subfield of AI for less than two decades. DAI is concerned with systems that consist of multiple independent entities that interact in a...

The RoboCup Synthetic Agent Challenge 97 (1997)

Hiroaki Kitano, Milind Tambe, Peter Stone, Manuela Veloso, Silvia Coradeschi, Eiichi Osawa, ...

RoboCup Challenge offers a set of challenges for intelligent agent researchers using a friendly competition in a dynamic, real-time, multiagent domain. While RoboCup in general envisions longer range...

A Layered Approach to Learning Client Behaviors in the RoboCup Soccer Server (1997)

Peter Stone, Manuela Veloso

In the past few years, Multiagent Systems (MAS) has emerged as an active subfield of Artificial Intelligence (AI). Because of the inherent complexity of MAS, there is much interest in using Machine...

The RoboCup Synthetic Agent Challenge 97 (1997)

Hiroaki Kitano, Milind Tambe, Peter Stone, Manuela Veloso, Silvia Coradeschi, Eiichi Osawa, ...

RoboCup Challenge offers a set of challenges for intelligent agent researchers using a friendly competition in a dynamic, real-time, multiagent domain. While RoboCup in general envisions longer range...

A Layered Approach for an Autonomous Robotic Soccer System (1997)

Manuela Veloso, Peter Stone, Sorin Achim

This paper is a very brief introduction to our work and the reader is referred to the references provided. We present the architecture of the physical system and introduce how actions are layered...

The RoboCup synthetic agent challenge 97 (1997)

Hiroaki Kitano, Milind Tambe, Peter Stone, Manuela Veloso, Silvia Coradeschi, Eiichi Osawa, ...

RoboCup Challenge o ers a set of challenges for intelligent agent researchers using a friendly competition in a dynamic, real-time, multiagent domain. While RoboCup in general envisions longer range...

The RoboCup Physical Agent Challenge: Phase-I (1997)

Minoru Asada, Peter Stone, Hiroaki Kitano, Barry Werger, Yasuo Kuniyoshi, Alexis Drogoul, ...

Traditional AI research has not given due attention to the important role that physical bodies play for agents as their interactions produce complex emergent behaviors to achieve goals in the dynamic...

The RoboCup synthetic agent challenge 97 (1997)

Hiroaki Kitano, Milind Tambe, Peter Stone, Manuela Veloso, Silvia Coradeschi, Eiichi Osawa, ...

matsubarfletl.go.jp nodafletl.go.jp asadaflmech.eng.osaka-u.ac.jp RoboCup Challenge offers a set of challenges for intelligent agent researchers using a friendly competition in a dynamic, real-time,...

Predictive memory for an inaccessible environment (1996)

Mike Bowling, Peter Stone, Manuela Veloso

Inaccessible and nondeterministic environ-ments are very common in real-world problems. One of the difficulties in these environments is representing the knowledge about the unknown aspects of the...

Adjusting to Policy Expectations in Climate Change Modeling: An Interdisciplinary Study to Flux Adjustments (1996)

Simon Shackley, James Risbey, Peter Stone, Brian Wynne

Abstract. This paper surveys and interprets the attitudes of scientists to the use of flux adjustments in climate projections with coupled Atmosphere Ocean General Circulation Models. The survey is...

Beating a Defender in Robotic Soccer: Memory-Based Learning of a Continuous Function (1996)

Peter Stone And, Peter Stone, Manuela Veloso

Learning how to adjust to an opponent's position is critical to the success of having intelligent agents collaborating towards the achievement of specific tasks in unfriendly environments. This...

Beating a Defender in Robotic Soccer: Memory-Based Learning of a Continuous Function (1996)

Peter Stone, Manuela Veloso

Learning how to adjust to an opponent's position is critical to the success of having intelligent agents collaborating towards the achievement of specific tasks in unfriendly environments. This...

Predictive Memory for an Inaccessible Environment (1996)

Mike Bowling, Peter Stone, Manuela Veloso

Inaccessible and nondeterministic environments are very common in real-world problems. One of the difficulties in these environments is representing the knowledge about the unknown aspects of the...

Predictive Memory for an Inaccessible Environment (1996)

Mike Bowling, Peter Stone, Manuela Veloso

Inaccessible and nondeterministic environments are very common in real-world problems. One of the difficulties in these environments is representing the knowledge about the unknown aspects of the...

Beating a Defender in Robotic Soccer: Memory-Based Learning of a Continuous Function (1996)

Peter Stone, Manuela Veloso

Learning how to adjust to an opponent's position is critical to the success of having intelligent agents collaborating towards the achievement of specific tasks in unfriendly environments. This...

Building a Dedicated Robotic Soccer System (1996)

Sorin Achim, Peter Stone, Manuela Veloso

Robotic Soccer involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. We have been building an architecture that addresses this integration of...

Building a dedicated robotic soccer system (1996)

Sorin Achim, Peter Stone, Manuela Veloso

Robotic Soccer involves multiple agents that need to collaborate in an adversarial environment toachieve speci c objectives. We have been building an architecture that addresses this integration of...

Beating a defender in robotic soccer: Memory-based learning of a continuous function (1996)

Peter Stone, Manuela Veloso

Learning how to adjust to an opponent's position is critical to the success of having intelligent agents collaborating towards the achievement of speci c tasks in unfriendly environments. This...

User-guided interleaving of planning and execution (1996)

Peter Stone, Manuela Veloso

We explore two advantages of interleaving execution with planning. First, the overall planning and execution time can be reduced. Second, information from the environment can be incorporated into the...

Predictive memory for an inaccessible environment (1996)

Mike Bowling, Peter Stone, Manuela Veloso

Inaccessible and nondeterministic environments are very common in real-world problems. One of the di culties in these environments is representing the knowledge about the unknown aspects of the...

FLECS: Planning with a flexible commitment strategy (1995)

Manuela Veloso, Peter Stone, Velosocs Cmu. Edu

There has been evidence that least-commitment planners can efficiently handle planning problems that involve difficult goal interactions. This evidence has led to the common belief that...

User-Guided Interleaving of Planning and Execution (1995)

Peter Stone, Manuela Veloso

We explore two advantages of interleaving execution with planning. First, the overall planning and execution time can be reduced. Second, information from the environment can be incorporated into the...

FLECS: Planning with a Flexible Commitment Strategy (1995)

Manuela Veloso, Peter Stone

There has been evidence that least-commitment planners can efficiently handle planning problems that involve difficult goal interactions. This evidence has led to the common belief that...

User-Guided Interleaving of Planning and Execution (1995)

Peter Stone, Manuela Veloso

We explore two advantages of interleaving execution with planning. First, the overall planning and execution time can be reduced. Second, information from the environment can be incorporated into the...

User-Guided Interleaving of Planning and Execution (1995)

Peter Stone, Manuela Veloso

. We explore two advantages of interleaving execution with planning. First, the overall planning and execution time can be reduced. Second, information from the environment can be incorporated into...

Broad Learning from Narrow Training: A Case Study in Robotic Soccer (1995)

Peter Stone, Manuela Veloso

The range of unseen instances that can be successfully classified by a learning algorithm is determined not only by the distribution of the training data, but also by the parameters of the function...

Veloso@cs.cmu.edu (1995)

Manuela Veloso, Peter Stone

There has been evidence that least-commitment planners can efficiently handle planning problems that involve difficult goal interactions. This evidence has led to the common belief that...

FLECS: Planning with a flexible commitment strategy (1995)

Manuela Veloso, Peter Stone

There has been evidence that least-commitment planners can e ciently handle planning problems that involve di cult goal interactions. This evidence has led to the common belief that...

FLECS: Planning with a flexible commitment strategy (1995)

Manuela Veloso, Peter Stone

There has been evidence that least-commitment planners can e ciently handle planning problems that involve di cult goal interactions. This evidence has led to the common belief that...

The need for different domain-independent heuristics (1994)

Peter Stone, Manuela Veloso, Jim Blythe

PRODIGY's planning lgorithm uses domain-independent search heuristics. In this paper, wc support our bclic that there is no single search heuristic that performs more efficiently than others for...

Learning to Solve Complex Planning Problems: Finding Useful Auxiliary Problems (1994)

Peter Stone, Manuela Veloso

Learning from past experience allows a problem solver to increase its solvability horizon from simple to complex problems. For planners, learning involves a training phase during which knowledge is...

The Need for Different Domain-Independent Heuristics (1994)

Peter Stone, Manuela Veloso, Jim Blythe

PRODIGY's planning algorithm uses domain-independent search heuristics. In this paper, we support our belief that there is no single search heuristic that performs more efficiently than others...

The Need for Different Domain-Independent Heuristics (1994)

Peter Stone, Manuela Veloso, Jim Blythe

prodigy's planning algorithm uses domain-independent search heuristics. In this paper, we support our belief that there is no single search heuristic that performs more e#ciently than others for...

The Need for Different Domain-Independent Heuristics (1994)

Peter Stone, Manuela Veloso, Jim Blythe

prodigy's planning algorithm uses domain-independent search heuristics. In this paper, we support our belief that there is no single search heuristic that performs more efficiently than others...

The Need for Different Domain-Independent Heuristics (1994)

Peter Stone, Manuela Veloso, Jim Blythe

prodigy's planning algorithm uses domain-independent search heuristics. In this paper, we support our belief that there is no single search heuristic that performs more efficiently than others...

The need for di erent domain-independent heuristics (1994)

Peter Stone, Manuela Veloso, Jim Blythe

prodigy's planning algorithm uses domain-indep endent search heuristics. In this paper, we support our belief that there is no single search heuristic that performs more e ciently than others...

The need for di erent domain-independent heuristics (1994)

Peter Stone, Manuela Veloso, Jim Blythe

prodigy's planning algorithm uses domain-independent search heuristics. In this paper, we support our belief that there is no single search heuristic that performs more e ciently than others for...

How to Ask Questions (1994)

Peter Stone

learning is not the answer.

Keeney,R.L.&Raiffa,H.Decisions with Multiple Objectives: Preferences and Value Tradeoffs (1976)

Nicholas K. Jong, Peter Stone

Model-based approaches to reinforcement learning exhibit low sample complexity while learning nearly optimal policies, but they are generally restricted to finite domains. Meanwhile, function...

Keeney,R.L.&Raiffa,H.Decisions with Multiple Objectives: Preferences and Value Tradeoffs (1976)

Nicholas K. Jong, Peter Stone

Model-based approaches to reinforcement learning exhibit low sample complexity while learning nearly optimal policies, but they are generally restricted to finite domains. Meanwhile, function...

Keeney,R.L.&Raiffa,H.Decisions with Multiple Objectives: Preferences and Value Tradeoffs (1976)

Nicholas K. Jong, Peter Stone

Model-based approaches to reinforcement learning exhibit low sample complexity while learning nearly optimal policies, but they are generally restricted to finite domains. Meanwhile, function...

Fibrations, cofibrations and homotopy equivalences /--by Peter Stone. (1973)

Stone, Peter.

Thesis (M. Sc.)--Memorial University of Newfoundland, 1973.

The Relationship between Ambient Air Pollution and Heart Rate Variability Differs for Individuals with Heart and Pulmonary Disease

Wheeler, Amanda, Zanobetti, Antonella, Gold, Diane R., Schwartz, Joel, Stone, Peter, Suh, Helen H.

Associations between concentrations of ambient fine particles [particulate matter < 2.5 μ m aerodynamic diameter (PM2.5)] and heart rate variability (HRV) have differed by study population. We...

The Relationship between Ambient Air Pollution and Heart Rate Variability Differs for Individuals with Heart and Pulmonary Disease

Wheeler, Amanda, Zanobetti, Antonella, Gold, Diane R., Schwartz, Joel, Stone, Peter, Suh, Helen H.

Associations between concentrations of ambient fine particles [particulate matter < 2.5 μ m aerodynamic diameter (PM2.5)] and heart rate variability (HRV) have differed by study population. We...