On the Relation between Policy Improvement and Off-Policy Minimum-Variance Policy Evaluation.
Alberto Maria MetelliSamuele MetaMarcello RestelliPublished in: UAI (2023)
Keyphrases
- policy evaluation
- minimum variance
- least squares
- reinforcement learning
- monte carlo
- policy iteration
- temporal difference
- markov decision processes
- model free
- variance reduction
- optimal policy
- function approximation
- portfolio optimization
- semi parametric
- statistical inference
- markov decision problems
- partially observable markov decision processes
- linear prediction
- reinforcement learning algorithms
- belief state
- evaluation function
- state space
- learning algorithm