A LEARNING ALGORITHM FOR COMMUNICATING MARKOV DECISION PROCESSES WITH UNKNOWN TRANSITION MATRICES

Bulletin of informatics and cybernetics ◽

10.5109/16771 ◽

2007 ◽

Vol 39 ◽

pp. 11-24

Author(s):

Tetsuichiro Iki ◽

Masayuki Horiguchi ◽

Masami Yasuda ◽

Masami Kurano

Keyword(s):

Markov Decision Processes ◽

Learning Algorithm ◽

Decision Processes ◽

Transition Matrices ◽

Markov Decision

Download Full-text

Learning algorithms for Markov decision processes

Journal of Applied Probability ◽

10.1017/s0021900200030825 ◽

1987 ◽

Vol 24 (01) ◽

pp. 270-276

Author(s):

Masami Kurano

Keyword(s):

Markov Decision Processes ◽

Optimal Policy ◽

Learning Algorithm ◽

Learning Algorithms ◽

Decision Processes ◽

The State ◽

Reward Structure ◽

Adaptive Policy ◽

Markov Decision ◽

Reward Criterion

This study is concerned with finite Markov decision processes whose dynamics and reward structure are unknown but the state is observable exactly. We establish a learning algorithm which yields an optimal policy and construct an adaptive policy which is optimal under the average expected reward criterion.

Download Full-text

A pulse neural network reinforcement learning algorithm for partially observable Markov decision processes

Systems and Computers in Japan ◽

10.1002/scj.10645 ◽

2005 ◽

Vol 36 (3) ◽

pp. 42-52 ◽

Cited By ~ 3

Author(s):

Koichiro Takita ◽

Masafumi Hagiwara

Keyword(s):

Neural Network ◽

Reinforcement Learning ◽

Markov Decision Processes ◽

Learning Algorithm ◽

Decision Processes ◽

Markov Decision ◽

Partially Observable Markov ◽

Partially Observable ◽

Reinforcement Learning Algorithm

Download Full-text

A novel Q-learning algorithm with function approximation for constrained Markov decision processes

2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton) ◽

10.1109/allerton.2012.6483246 ◽

2012 ◽

Cited By ~ 3

Author(s):

K. Lakshmanan ◽

Shalabh Bhatnagar

Keyword(s):

Markov Decision Processes ◽

Function Approximation ◽

Learning Algorithm ◽

Decision Processes ◽

Q Learning ◽

Constrained Markov Decision Processes ◽

Markov Decision

Download Full-text

A sampled fictitious play based learning algorithm for infinite horizon Markov Decision Processes

Proceedings of the 2011 Winter Simulation Conference (WSC) ◽

10.1109/wsc.2011.6148098 ◽

2011 ◽

Cited By ~ 4

Author(s):

Esra Sisikoglu ◽

Marina A. Epelman ◽

Robert L. Smith

Keyword(s):

Markov Decision Processes ◽

Learning Algorithm ◽

Infinite Horizon ◽

Decision Processes ◽

Fictitious Play ◽

Markov Decision

Download Full-text

Robust Optimality for Discounted Infinite-Horizon Markov Decision Processes With Uncertain Transition Matrices

IEEE Transactions on Automatic Control ◽

10.1109/tac.2008.930182 ◽

2008 ◽

Vol 53 (9) ◽

pp. 2112-2116 ◽

Cited By ~ 6

Author(s):

Baohua Li ◽

Jennie Si

Keyword(s):

Markov Decision Processes ◽

Infinite Horizon ◽

Decision Processes ◽

Transition Matrices ◽

Markov Decision

Download Full-text

Approximate Robust Policy Iteration Using Multilayer Perceptron Neural Networks for Discounted Infinite-Horizon Markov Decision Processes With Uncertain Correlated Transition Matrices

IEEE Transactions on Neural Networks ◽

10.1109/tnn.2010.2050334 ◽

2010 ◽

Vol 21 (8) ◽

pp. 1270-1280 ◽

Cited By ~ 14

Author(s):

Baohua Li ◽

J Si

Keyword(s):

Neural Networks ◽

Markov Decision Processes ◽

Multilayer Perceptron ◽

Infinite Horizon ◽

Policy Iteration ◽

Decision Processes ◽

Transition Matrices ◽

Markov Decision

Download Full-text

A learning algorithm for Markov decision processes with adaptive state aggregation

Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187) ◽

10.1109/cdc.2000.912220 ◽

2002 ◽

Cited By ~ 7

Author(s):

J.S. Baras ◽

V.S. Borkar

Keyword(s):

Markov Decision Processes ◽

Learning Algorithm ◽

Decision Processes ◽

State Aggregation ◽

Markov Decision

Download Full-text

An inverse reinforcement learning algorithm for semi-Markov decision processes

2017 IEEE Symposium Series on Computational Intelligence (SSCI) ◽

10.1109/ssci.2017.8280816 ◽

2017 ◽

Cited By ~ 1

Author(s):

Chuanfang Tan ◽

Yanjie Li ◽

Yuhu Cheng

Keyword(s):

Reinforcement Learning ◽

Markov Decision Processes ◽

Learning Algorithm ◽

Decision Processes ◽

Inverse Reinforcement Learning ◽

Markov Decision ◽

Reinforcement Learning Algorithm

Download Full-text

A Structure-aware Online Learning Algorithm for Markov Decision Processes

Proceedings of the 12th EAI International Conference on Performance Evaluation Methodologies and Tools - VALUETOOLS 2019 ◽

10.1145/3306309.3306321 ◽

2019 ◽

Cited By ~ 1

Author(s):

Arghyadip Roy ◽

Vivek Borkar ◽

Abhay Karandikar ◽

Prasanna Chaporkar

Keyword(s):

Online Learning ◽

Markov Decision Processes ◽

Learning Algorithm ◽

Decision Processes ◽

Markov Decision ◽

Online Learning Algorithm

Download Full-text

A Sublinear-Regret Reinforcement Learning Algorithm on Constrained Markov Decision Processes with reset action

Proceedings of the 4th International Conference on Machine Learning and Soft Computing ◽

10.1145/3380688.3380706 ◽

2020 ◽

Author(s):

Takashi Watanabe ◽

Takashi Sakuragawa

Keyword(s):

Reinforcement Learning ◽

Markov Decision Processes ◽

Learning Algorithm ◽

Decision Processes ◽

Constrained Markov Decision Processes ◽

Markov Decision ◽

Reinforcement Learning Algorithm

Download Full-text