Policy-Adaptive Estimator Selection for Off-Policy Evaluation.
Takuma UdagawaHaruka KiyoharaYusuke NaritaYuta SaitoKei TatenoPublished in: AAAI (2023)
Keyphrases
- policy evaluation
- least squares
- variance reduction
- monte carlo
- reinforcement learning
- temporal difference
- policy iteration
- markov decision processes
- model free
- function approximation
- semi parametric
- optimal policy
- statistical inference
- importance sampling
- partially observable
- partially observable markov decision processes
- policy gradient
- machine learning