Causal Bandits with General Causal Models and Interventions

Z Yan, D Wei, DA Katz, P Sattigeri… - … Conference on Artificial …, 2024 - proceedings.mlr.press
This paper considers causal bandits (CBs) for the sequential design of interventions in a
causal system. The objective is to optimize a reward function via minimizing a measure of …

Learning Mixtures of Unknown Causal Interventions

A Kumar, K Shiragur, C Uhler - arxiv preprint arxiv:2411.00213, 2024 - arxiv.org
The ability to conduct interventions plays a pivotal role in learning causal relationships
among variables, thus facilitating applications across diverse scientific disciplines such as …

Linear Causal Bandits: Unknown Graph and Soft Interventions

Z Yan, A Tajer - arxiv preprint arxiv:2411.02383, 2024 - arxiv.org
Designing causal bandit algorithms depends on two central categories of assumptions:(i)
the extent of information about the underlying causal graphs and (ii) the extent of information …

Improved Bound for Robust Causal Bandits with Linear Models

Z Yan, A Mukherjee, B Varıcı, A Tajer - arxiv preprint arxiv:2405.07795, 2024 - arxiv.org
This paper investigates the robustness of causal bandits (CBs) in the face of temporal model
fluctuations. This setting deviates from the existing literature's widely-adopted assumption of …