A learning algorithm for Markov decision processes with adaptive state aggregation

2002 ◽  
Author(s):  
J.S. Baras ◽  
V.S. Borkar
Keyword(s):  
Markov Decision Processes ◽  
Learning Algorithm ◽  
Decision Processes ◽  
State Aggregation ◽  
Markov Decision

Learning algorithms for Markov decision processes

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.

Sign in / Sign up

Export Citation Format

Share Document