Uncertainty quantification for operators in online reinforcement learning.
Bi WangJianqing WuXuelian LiJun ShenYangjun ZhongPublished in: Knowl. Based Syst. (2022)
Keyphrases
- reinforcement learning
- online learning
- multi agent
- partial observability
- state space
- function approximation
- optimal policy
- balancing exploration and exploitation
- model free
- real time
- dynamic programming
- markov decision processes
- online communities
- reinforcement learning algorithms
- uncertain information
- search engine
- neural network