Average-Reward Off-Policy Policy Evaluation with Function Approximation.
Shangtong ZhangYi WanRichard S. SuttonShimon WhitesonPublished in: CoRR (2021)
Keyphrases
- function approximation
- average reward
- policy evaluation
- model free
- reinforcement learning
- policy iteration
- temporal difference
- td learning
- markov decision processes
- optimal policy
- reinforcement learning algorithms
- learning tasks
- long run
- policy gradient
- state space
- function approximators
- dynamic programming
- learning algorithm
- machine learning
- radial basis function
- partially observable
- transfer learning