BA-UCB identifies candidate backdoor sets from sequential data to estimate causal effects and construct UCBs for intervention selection in unknown-graph causal bandits, with regret bounds and extension to latent confounders.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Identifiable latent bandits apply nonlinear ICA to observational data to recover representations sufficient for inferring optimal actions in new instances, shortening exploration time.
citing papers explorer
-
Causal Bandit Over Unknown Graphs: Upper Confidence Bounds With Backdoor Adjustment
BA-UCB identifies candidate backdoor sets from sequential data to estimate causal effects and construct UCBs for intervention selection in unknown-graph causal bandits, with regret bounds and extension to latent confounders.
-
Identifiable Latent Bandits: Leveraging observational data for personalized decision-making
Identifiable latent bandits apply nonlinear ICA to observational data to recover representations sufficient for inferring optimal actions in new instances, shortening exploration time.