A Review of Off-Policy Evaluation in Reinforcement Learning.
Masatoshi UeharaChengchun ShiNathan KallusPublished in: CoRR (2022)
Keyphrases
- policy evaluation
- reinforcement learning
- temporal difference
- least squares
- model free
- monte carlo
- function approximation
- policy iteration
- markov decision processes
- td learning
- variance reduction
- reinforcement learning algorithms
- partially observable markov decision processes
- optimal policy
- semi parametric
- state space
- learning algorithm
- evaluation function
- supervised learning
- multi agent
- learning tasks
- transfer learning
- optimal control
- cost function
- statistical inference
- reinforcement learning methods
- markov decision problems
- markov chain