Hierarchical Causal Bandit

03/07/2021
by   Ruiyang Song, et al.
0

Causal bandit is a nascent learning model where an agent sequentially experiments in a causal network of variables, in order to identify the reward-maximizing intervention. Despite the model's wide applicability, existing analytical results are largely restricted to a parallel bandit version where all variables are mutually independent. We introduce in this work the hierarchical causal bandit model as a viable path towards understanding general causal bandits with dependent variables. The core idea is to incorporate a contextual variable that captures the interaction among all variables with direct effects. Using this hierarchical framework, we derive sharp insights on algorithmic design in causal bandits with dependent arms and obtain nearly matching regret bounds in the case of a binary context.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/16/2022

Pure Exploration of Causal Bandits

Causal bandit problem integrates causal inference with multi-armed bandi...
research
02/10/2022

Adaptively Exploiting d-Separators with Causal Bandits

Multi-armed bandit problems provide a framework to identify the optimal ...
research
01/26/2023

Causal Bandits without Graph Learning

We study the causal bandit problem when the causal graph is unknown and ...
research
08/07/2023

Provably Efficient Learning in Partially Observable Contextual Bandit

In this paper, we investigate transfer learning in partially observable ...
research
06/04/2022

Combinatorial Causal Bandits

In combinatorial causal bandits (CCB), the learning agent chooses at mos...
research
09/16/2020

Causal Discovery for Causal Bandits utilizing Separating Sets

The Causal Bandit is a variant of the classic Bandit problem where an ag...
research
01/29/2023

Contextual Causal Bayesian Optimisation

Causal Bayesian optimisation (CaBO) combines causality with Bayesian opt...

Please sign up or login with your details

Forgot password? Click here to reset