Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models.
Michael OberstDavid A. SontagPublished in: ICML (2019)
Keyphrases
- causal models
- policy evaluation
- causal reasoning
- structural model
- least squares
- reinforcement learning
- causal discovery
- markov decision processes
- model free
- monte carlo
- conditional independence
- temporal difference
- policy iteration
- causal relationships
- directed acyclic graph
- variance reduction
- function approximation
- structural equation models
- machine learning
- gaussian process
- semi parametric
- finite state
- linear model
- optimal policy
- markov chain
- state space