Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning.
Cameron VoloshinHoang Minh LeNan JiangYisong YuePublished in: NeurIPS Datasets and Benchmarks (2021)
Keyphrases
- empirical studies
- policy evaluation
- reinforcement learning
- temporal difference
- least squares
- model free
- markov decision processes
- monte carlo
- function approximation
- policy iteration
- td learning
- optimal policy
- semi parametric
- state space
- variance reduction
- empirical analysis
- reinforcement learning algorithms
- learning algorithm
- multi agent
- evaluation function
- action selection
- statistical inference
- markov decision problems
- transfer learning
- cost function
- reinforcement learning methods