Fully asynchronous policy evaluation in distributed reinforcement learning over networks.
Xingyu ShaJiaqi ZhangKeyou YouKaiqing ZhangTamer BasarPublished in: Autom. (2022)
Keyphrases
- policy evaluation
- reinforcement learning
- temporal difference
- model free
- least squares
- function approximation
- policy iteration
- monte carlo
- markov decision processes
- td learning
- multi agent
- variance reduction
- optimal policy
- semi parametric
- state space
- learning algorithm
- machine learning
- reinforcement learning algorithms
- statistical inference
- action selection
- np hard