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

Tetsuichiro Iki | Zendy; Masayuki Horiguchi | Zendy; Masami Yasuda | Zendy; Masami Kurano | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

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

Author(s) -

Tetsuichiro Iki,

Masayuki Horiguchi,

Masami Yasuda,

Masami Kurano

Publication year - 2007

Publication title -

bulletin of informatics and cybernetics

Language(s) - English

Resource type - Journals

eISSN - 2435-743X

pISSN - 0286-522X

DOI - 10.5109/16771

Subject(s) - markov decision process , transition (genetics) , markov chain , computer science , stochastic matrix , markov model , algorithm , markov process , artificial intelligence , machine learning , mathematics , statistics , chemistry , biochemistry , gene

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 type for the communicating case of multi-chain MDPs. An adaptively optimal policy and an asymptotic sequence of adaptive policies with nearly optimal properties are constructed under the average expected reward criterion. Also, a numerical experiment is given to show the practical effectiveness of the algorithm.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research