Average-Reward Off-Policy Policy Evaluation with Function Approximation.
Shangtong ZhangYi WanRichard S. SuttonShimon WhitesonPublished in: ICML (2021)
Keyphrases
- average reward
- function approximation
- policy evaluation
- model free
- reinforcement learning
- policy iteration
- temporal difference
- markov decision processes
- optimal policy
- reinforcement learning algorithms
- td learning
- radial basis function
- learning tasks
- state space
- function approximators
- state action
- long run
- multi agent
- reinforcement learning methods
- active learning
- learning algorithm
- machine learning
- neural network
- real valued