Off-Policy Evaluation for Action-Dependent Non-Stationary Environments.
Yash ChandakShiv ShankarNathaniel D. BastianBruno Castro da SilvaEmma BrunskillPhilip S. ThomasPublished in: CoRR (2023)
Keyphrases
- policy evaluation
- least squares
- temporal difference
- reinforcement learning
- action selection
- model free
- monte carlo
- markov decision processes
- policy iteration
- function approximation
- variance reduction
- semi parametric
- statistical inference
- support vector
- optimal control
- learning algorithm
- fixed point
- optimal policy
- active learning
- decision making