Provably Efficient Causal Reinforcement Learning with Confounded Observational Data.

Lingxiao Wang Zhuoran Yang Zhaoran Wang

Published in: CoRR (2020)

Keyphrases

observational data
reinforcement learning
causal discovery
experimental data
causal relationships
causal inference
causal structure
causal models
causal bayesian networks
feature selection
latent variables
databases
worst case
bayesian networks
machine learning
random variables
optimal policy
special case