A New Reinforcement Learning Algorithm With Fixed Exploration for Semi-Markov Control in Preventive Maintenance

2017 ◽  
Author(s):  
Angelo Encapera ◽  
Abhijit Gosavi
Keyword(s):  
Reinforcement Learning ◽  
Markov Decision Processes ◽  
Numerical Experiments ◽  
Learning Algorithm ◽  
Decision Processes ◽  
Control Problems ◽  
Total Productive Maintenance ◽  
Markov Decision ◽  
Markov Control ◽  
Reinforcement Learning Algorithm

Artificial intelligence techniques can play a significant role in solving problems encountered in the domain of Total Productive Maintenance (TPM). This paper considers a new reinforcement learning algorithm called iSMART, which can solve semi-Markov decision processes underlying control problems related to TPM. The algorithm uses a constant exploration rate, unlike its precursor R-SMART, which required exploration decay. Numerical experiments conducted here show encouraging behavior with the new algorithm.

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