Research map / Bandits and online learning / Contextual bandits and Thompson sampling

Multi-Objective Causal Bandits: Minimal Intervention Space and Policy-Level Learning

NeurIPS 2026 · Bandits and online learning › Contextual bandits and Thompson sampling · approach: Causal and structured bandits

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies multi-objective causal bandits with multiple reward nodes, where actions are interventions on variable subsets and performance is judged by Pareto optimality.

Problem

Multi-objective decision-making where interventions on causal graph variables affect several reward metrics, fairness criteria, or safety constraints, and existing multi-objective bandit approaches do not exploit causal structure.

Approach

Frames actions as interventions on subsets of causal graph variables with Pareto-optimality evaluation across multiple reward nodes, and introduces a minimal intervention space and policy-level learning; the abstract is truncated so specifics beyond this are not stated.

Closest papers by meaning

• Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · similarity 0.93)
• Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits (NeurIPS 2024 · similarity 0.92)
• Linear Causal Bandits: Unknown Graph and Soft Interventions (NeurIPS 2024 · similarity 0.90)
• Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approach (AAAI 2024 · similarity 0.88)
• Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · similarity 0.88)
• Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk (NeurIPS 2026 · similarity 0.88)