Timezone: »

 
Poster
Causal Bandits with Unknown Graph Structure
Yangyi Lu · Amirhossein Meisami · Ambuj Tewari

Thu Dec 09 12:30 AM -- 02:00 AM (PST) @
in Poster Session 5 »

In causal bandit problems the action set consists of interventions on variables of a causal graph. Several researchers have recently studied such bandit problems and pointed out their practical applications. However, all existing works rely on a restrictive and impractical assumption that the learner is given full knowledge of the causal graph structure upfront. In this paper, we develop novel causal bandit algorithms without knowing the causal graph. Our algorithms work well for causal trees, causal forests and a general class of causal graphs. The regret guarantees of our algorithms greatly improve upon those of standard multi-armed bandit (MAB) algorithms under mild conditions. Lastly, we prove our mild conditions are necessary: without them one cannot do better than standard MAB algorithms.

Keywords: Graph Learning · Bandits · Causality

Author Information

Yangyi Lu (University of Michigan)
Amirhossein Meisami (University of Michigan)
Ambuj Tewari (University of Michigan)

More from the Same Authors