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

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

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.

scholarly journals Safe Q-Learning Method Based on Constrained Markov Decision Processes

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 165007-165017 ◽  
Author(s):  
Yangyang Ge ◽  
Fei Zhu ◽  
Xinghong Ling ◽  
Quan Liu
Keyword(s):  
Markov Decision Processes ◽  
Decision Processes ◽  
Learning Method ◽  
Q Learning ◽  
Constrained Markov Decision Processes ◽  
Markov Decision
Sign in / Sign up

Export Citation Format

Share Document