Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making.
Sonali ParbhooShalmali JoshiFinale Doshi-VelezPublished in: CoRR (2022)
Keyphrases
- sequential decision making
- policy evaluation
- temporal difference
- reinforcement learning
- model free
- function approximation
- evaluation function
- monte carlo
- reinforcement learning algorithms
- step size
- policy iteration
- least squares
- decision problems
- markov decision processes
- action selection
- convergence rate
- learning tasks
- learning algorithm
- machine learning
- supervised learning
- dynamic programming
- bayesian networks
- influence diagrams
- state space