Causally Abstracted Multi-armed Bandits

arXiv:2404.17493v1 Announce Type: new
Abstract: Multi-armed bandits (MAB) and causal MABs (CMAB) are established frameworks for decision-making problems. The majority of prior work typically studies and solves individual MAB and CMAB in isolation for a given problem and associated data. However, decision-makers are often faced with multiple related problems and multi-scale observations where joint formulations are needed in order to efficiently exploit the problem structures and data dependencies. Transfer learning for CMABs addresses the situation where models are defined on …

abstract arxiv causal cs.ai cs.lg data decision frameworks however makers making multi-armed bandits multiple prior scale studies type work