Research map / Bandits and online learning / Online convex optimization and games

Online Learning of Group-Stable Coalition Structures

NeurIPS 2026 · Bandits and online learning › Online convex optimization and games · approach: Online decision-making with feedback structure

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 online learning of group-stable coalition structures, where coalitions are formed repeatedly from preferences learned from iterative feedback.

Problem

Coalition formation when agents' preferences over one another are initially unknown, so coalitions must be formed repeatedly based on preferences learned online from feedback within coalitions.

Approach

Introduces a new group stability approach to online coalition structure learning; the abstract is truncated so the specific mechanism is not stated.

Closest papers by meaning

• Online Learning of Coalition Structures by Selfish Agents (AAAI 2025 · similarity 0.93)
• Stability in Online Coalition Formation (AAAI 2024 · similarity 0.91)
• Deviate or Not: Learning Coalition Structures with Multiple-bit Observations in Games (AAAI 2025 · similarity 0.89)
• Learning Coalition Structures with Games (AAAI 2024 · similarity 0.88)
• Individually Stable Dynamics in Coalition Formation over Graphs (AAAI 2025 · similarity 0.87)
• Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos (AAAI 2024 · similarity 0.86)