Provably Efficient Causal Reinforcement Learning with Confounded Observational Data.

Lingxiao Wang Zhuoran Yang Zhaoran Wang

Published in: NeurIPS (2021)

Keyphrases

observational data
reinforcement learning
causal discovery
causal bayesian networks
causal models
causal structure
causal inference
causal relationships
bayesian networks
experimental data
directed acyclic graph
prior knowledge
state space
markov decision processes
causal relations
causal effects