A FUZZY PERCEPTIVE VALUE FOR MULTI-VARIATE STOPPING PROBLEM WITH A MONOTONE RULE (2007)
Kurano, Masami, Yasuda, Masami, Nakagami, Jun-ichi, Yoshida, Yuji, 蔵野, 正美, 安田, 正實, ...
This paper discusses a perception-based theory for a multi-variate stopping problem with a monotone rule by Yasuda et al. (1982). The problem is developed by using the perceptive analysis of the...
Iki, Tetsuichiro, Horiguchi, Masayuki, Yasuda, Masami, Kurano, Masami, 伊喜, 哲一郎, 安田, 正實, ...
This study is concerned with finite Markov decision processes (MDPs) whose state are exactly observable but its transition matrix is unknown. We develop a learning algorithm of the reward-penalty...
CLUSTERING BY A FUZZY METRIC : APPLICATIONS TO THE CLUSTER-MEDIAN PROBLEM (2000)
Kamimura, Hideki, Kurano, Masami, 上村, 英樹, 蔵野, 正美
This paper is the second part of our study of the clustering problem with a fuzzy metric. The fuzzy metric between any two elements will be constructed from the multi-dimensional fuzzy data available...
A MONOTONE FUZZY STOPPING TIME IN DYNAMIC FUZZY SYSTEMS (1999)
Yoshida, Yuji, Yasuda, Masami, Nakagami, Jun-ichi, Kurano, Masami, 吉田, 祐治, 安田, 正實, ...
This paper is concerned with a fuzzy stopping time for a dynamic fuzzy system. A new class of fuzzy stopping times which is called as a monotone fuzzy stopping time is introduced. The notion of...
UTILITY-OPTIMAL STOPPING IN A DENUMERABLE MARKOV CHAIN (1996)
Kadota, Yoshinobu, Kurano, Masami, Yasuda, Masami, 門田, 良信, 蔵野, 正美, 安田, 正實
This paper is concerned with a general utility of the optimal stopping problem for denumerable Markov chains. The validity of the one-step look ahead (OLA) stopping time is shown under a general...
A UTILITY DEVIATION IN DISCOUNTED MARKOV DECISION PROCESSES WITH GENERAL UTILITY (1996)
Kadota, Yoshinobu, Kurano, Masami, Yasuda, Masami, 門田, 良信, 蔵野, 正美, 安田, 正實
A utility treatment is studied in the framework of discounted Markov decision processes. We will define a new index called a utility deviation related to the risk premium, which is characterized by...
ON EFFICIENCY OF INFERENCES OF TRANSITION PROBABILITIES TO MARKOVIAN DECISION PROCESSES (1973)
Kobayashi, Kingo, Fujikawa, H., Kurano, Masami, 小林, 欣吾, 蔵野, 正美
A Span Seminorm Approach to Controlled Markov Set-Chains
ホサカ, マサノリ, 蔵野, 正美, クラノ, マサミ, Hosaka, Masanori, Kurano, Masami
In a controlled Markov set-chain with finite state and action spaces, we find a policy, called average-optimal, which maximizes Cesaro sums of each time's reward over all stationaly policies under...
A Span Seminorm Approach to Controlled Markov Set-Chains(III : Natural Sciences)
ホサカ, マサノリ, Hosaka, Masanori, HOSAKA, Masanori, KURANO, Masami, 蔵野, 正美, クラノ, マサミ, ...
In a controlled Markov set-chain with finite state and action spaces, we find a policy, called average-optimal, which maximizes Cesaro sums of each time's reward over all stationaly policies under...
The LP Approach In Average Reward MDPs With Multiple Cost Constraints : The Unbounded Case
Huang, Youqiang, 蔵野, 正美, クラノ, マサミ, Kurano, Masami
In this paper we study constrained Markov decision processes with countable states and unbounded reward. A corresponding linear programming and its dual are formulated. Under some reasonable...
Huang, Youqiang, Kurano, Masami, 蔵野, 正美, クラノ, マサミ
In this paper we study constrained Markov decision processes with countable states and unbounded reward. A corresponding linear programming and its dual are formulated. Under some reasonable...
A Span Seminorm Approach to Controlled Markov Set-Chains
ホサカ, マサノリ, 蔵野, 正美, クラノ, マサミ, Hosaka, Masanori, Kurano, Masami
In a controlled Markov set-chain with finite state and action spaces, we find a policy, called average-optimal, which maximizes Cesaro sums of each time's reward over all stationaly policies under...
The LP Approach In Average Reward MDPs With Multiple Cost Constraints : The Unbounded Case
Huang, Youqiang, 蔵野, 正美, クラノ, マサミ, Kurano, Masami
In this paper we study constrained Markov decision processes with countable states and unbounded reward. A corresponding linear programming and its dual are formulated. Under some reasonable...