On Instrumental Variable Regression for Deep Offline Policy Evaluation.
Yutian ChenLiyuan XuÇaglar GülçehreTom Le PaineArthur GrettonNando de FreitasArnaud DoucetPublished in: J. Mach. Learn. Res. (2022)
Keyphrases
- policy evaluation
- semi parametric
- least squares
- linear regression
- monte carlo
- temporal difference
- reinforcement learning
- regression model
- model free
- markov decision processes
- policy iteration
- regression problems
- function approximation
- variance reduction
- support vector
- model selection
- genetic programming
- statistical inference
- machine learning
- state space
- bayesian networks
- learning algorithm