Policy Learning: A Unified Perspective with Applications in Robotics (2008)
Peters, J., Kober, J., Nguyen-Tuong, D., Girgin, S., Loth, M., Munos, R., ...
Policy Learning approaches are among the best suited methods for high-dimensional, continuous control systems such as anthropomorphic robot arms and humanoid robots. In this paper, we show two...
Probabilistic Inference for Fast Learning in Control (2008)
Rasmussen, C.E., Deisenroth, M.P., Girgin, S., Loth, M., Munos, R., Preux, P., ...
We provide a novel framework for very fast model-based reinforcement learning in continuous state and action spaces. The framework requires probabilistic models that explicitly characterize their...
An anti-diffusive scheme for viability problems (2006)
Bokanowski, O., Martin, S., Munos, R., Zidani, H.
The value function associated with viability problem is discontinuous. We investigate the Ultra-Bee scheme, particularly interesting for its anti-diffusive property in the transport of discontinuous...
Umr Cnrs, E. Gobet, R. Munos, Emmanuel Gobet
We consider a multidimensional diusion process (X t ) 0tT whose dynamics depends on parameters . Our rst purpose is to give representation formulae of the sensitivity rJ() for the expected cost J() =...
A general convergence method for Reinforcement Learning in the continuous case (1998)
In this paper, we propose a general method for designing convergent Reinforcement Learning algorithms in the case of continuous state-space and time variables. The method is based on the...
Reinforcement learning for continuous stochastic control problems (1998)
This paper is concerned with the problem of reinforcement learning (RL) for continuous state space and time stochastic control problems. We state the Hamilton-Jacobi-Bellman equation satisfied by the...
This paper presents a reinforcement learning algorithm designed for solving optimal control problems for which state space and time are continuous variables. Like Dynamic Programming methods,...
Apprentissage par renforcement, étude du cas continu (1997)
This thesis intends to deal with the problem: how is it possible to define some methods allowing an artificial system to " learn from experience "? That is to solve some problem without being...
This paper proposes to use the reinforcement learning framework to put in prominent position the cognitive processes used when a system interacts with its environment by taking sequences of...
In this paper, we propose a convergent reinforcement learning algorithm for solving optimal control problems for which state space and time are continuous variables. The problem of computing a good...
This paper presents a reinforcement learning method for solving continuous optimal control problems when the dynamics of the system is unknown. First, we use a finite differences method for...
This paper presents a direct reinforcement learning algorithm, called Finite Element Reinforcement Learning, in the continuous case. We propose a continuous formalism for the studying of...
Reinforcement learning with dynamic covering of state-action space : Partitioning Q-learning (1994)
This paper presents a reinforcement learning algorithm : "Partitioning Q-learning", designed for generating an adaptive behavior of a reactive system with local perception in a complex and changing...