Cohesion-driven Online Actor-Critic Reinforcement Learning for mHealth Intervention.
Feiyun ZhuPeng LiaoXinliang ZhuJiawen YaoJunzhou HuangPublished in: BCB (2018)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- reinforcement learning algorithms
- temporal difference
- approximate dynamic programming
- optimal control
- function approximation
- policy iteration
- neuro fuzzy
- gradient method
- state space
- learning algorithm
- control problems
- model free
- markov decision processes
- policy gradient methods
- markov decision process
- linear program
- dynamic programming
- control strategy
- evaluation function
- average reward
- recursive least squares
- rl algorithms
- mobile robot
- machine learning