Distributional Off-policy Evaluation with Bellman Residual Minimization.
Sungee HongZhengling QiRaymond K. W. WongPublished in: CoRR (2024)
Keyphrases
- policy evaluation
- bellman residual
- least squares
- policy iteration
- markov decision processes
- reinforcement learning
- temporal difference
- monte carlo
- model free
- variance reduction
- function approximation
- semi parametric
- optimal policy
- fixed point
- objective function
- hybrid algorithms
- statistical inference
- markov decision process
- infinite horizon
- partially observable markov decision processes
- average cost
- machine learning
- gaussian process
- dynamic programming
- learning algorithm