Cross-Validated Off-Policy Evaluation.
Matej CiefBranislav KvetonMichal KompanPublished in: CoRR (2024)
Keyphrases
- cross validated
- policy evaluation
- least squares
- cross validation
- monte carlo
- temporal difference
- reinforcement learning
- model free
- markov decision processes
- log likelihood
- policy iteration
- variance reduction
- function approximation
- semi parametric
- fold cross validation
- optimal policy
- model selection
- linear regression
- bayesian classifiers
- hyperparameters
- dynamic programming
- logistic regression
- genetic programming
- state space
- training set
- support vector