Offline Policy Evaluation for Reinforcement Learning with Adaptively Collected Data.
Sunil MadhowDan XiaoMing YinYu-Xiang WangPublished in: CoRR (2023)
Keyphrases
- collected data
- policy evaluation
- reinforcement learning
- temporal difference
- least squares
- model free
- function approximation
- data collection
- policy iteration
- markov decision processes
- td learning
- monte carlo
- variance reduction
- optimal policy
- semi parametric
- reinforcement learning algorithms
- data sources
- machine learning
- state space
- gaussian process
- learning algorithm
- action selection
- multi agent
- evaluation function
- function approximators
- dynamic programming
- sensor networks
- statistical inference
- supervised learning
- reinforcement learning methods
- markov decision problems
- transfer learning