Cohesion-based Online Actor-Critic Reinforcement Learning for mHealth Intervention.
Feiyun ZhuPeng LiaoXinliang ZhuYaowen YaoJunzhou HuangPublished in: CoRR (2017)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- optimal control
- temporal difference
- approximate dynamic programming
- function approximation
- reinforcement learning algorithms
- gradient method
- policy iteration
- neuro fuzzy
- model free
- markov decision processes
- policy gradient methods
- state space
- multi agent
- natural actor critic
- average reward
- transfer learning
- optimal policy
- learning algorithm
- infinite horizon
- learning problems
- control problems