Off-Policy Evaluation with Policy-Dependent Optimization Response.
Wenshuo GuoMichael I. JordanAngela ZhouPublished in: CoRR (2022)
Keyphrases
- policy evaluation
- least squares
- reinforcement learning
- temporal difference
- monte carlo
- policy iteration
- model free
- optimal policy
- variance reduction
- markov decision processes
- function approximation
- optimization algorithm
- statistical inference
- constrained optimization
- semi parametric
- evaluation function
- partially observable markov decision processes
- sufficient conditions
- probabilistic model
- learning algorithm
- average reward
- action selection
- belief revision
- graphical models
- supervised learning