Average Reward Reinforcement Learning for Semi-Markov Decision Processes.
Jiayuan YangYanjie LiHaoyao ChenJiangang LiPublished in: ICONIP (1) (2017)
Keyphrases
- average reward reinforcement learning
- semi markov decision processes
- optimal policy
- average reward
- markov decision processes
- reinforcement learning
- state space
- dynamic programming
- decision problems
- infinite horizon
- finite state
- long run
- sufficient conditions
- initial state
- machine learning
- markov decision process
- policy iteration
- domain specific
- markov decision problems
- bayesian networks
- decision making