A Causal Bandit Approach to Learning Good Atomic Interventions in Presence of Unobserved Confounders. (arXiv:2107.02772v2 [cs.LG] UPDATED)

We study the problem of determining the best intervention in a Causal
Bayesian Network (CBN) specified only by its causal graph. We model this as a
stochastic multi-armed bandit (MAB) problem with side-information, where the
interventions correspond to the arms of the bandit instance. First, we propose
a simple regret minimization algorithm that takes as input a semi-Markovian
causal graph with atomic interventions and possibly unobservable variables, and
achieves $\tilde{O}(\sqrt{M/T})$ expected simple regret, where $M$ is dependent
on the input …

arxiv good learning