Online Estimation and Inference for Robust Policy Evaluation in Reinforcement Learning.
Weidong LiuJiyuan TuYichen ZhangXi ChenPublished in: CoRR (2023)
Keyphrases
- policy evaluation
- reinforcement learning
- temporal difference
- model free
- function approximation
- semi parametric
- least squares
- policy iteration
- monte carlo
- markov decision processes
- td learning
- estimation error
- statistical inference
- reinforcement learning algorithms
- variance reduction
- optimal policy
- state space
- evaluation function
- learning algorithm
- density estimation
- gaussian process
- bayesian inference
- probabilistic model
- dynamic programming
- multi agent
- bayesian networks
- decision making