Cooperative Open-ended Learning Framework For Zero-shot Coordination

Abstract

Zero-shot coordination in cooperative artificial intelligence (AI) remains a significant challenge, which means effectively coordinating with a wide range of unseen partners. Previous algorithms have attempted to address this challenge by optimizing fixed objectives within a population to improve strategy or behaviour diversity. However, these approaches can result in a loss of learning and an inability to cooperate with certain strategies within the population, known as cooperative incompatibility. To address this issue, we propose the Cooperative Open-ended LEarning (COLE) framework, which constructs open-ended objectives in cooperative games with two players from the perspective of graph theory to assess and identify the cooperative ability of each strategy. We further specify the framework and propose a practical algorithm that leverages knowledge from game theory and graph theory. Furthermore, an analysis of the learning process of the algorithm shows that it can efficiently overc

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2023cooperative

Related papers

• Tackling Cooperative Incompatibility For Zero-shot Human-ai Coordination (2023)0.00
• "other-play" For Zero-shot Coordination (2020)0.00
• A New Formalism, Method And Open Issues For Zero-shot Coordination (2021)0.00
• Heterogeneous Multi-agent Zero-shot Coordination By Coevolution (2022)5.24
• Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination (2025)0.00
• Knowpc: Knowledge-driven Programmatic Reinforcement Learning For Zero-shot Coordination (2024)0.00
• Open Ad Hoc Teamwork With Cooperative Game Theory (2024)1.40
• Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In The Game Of Hanabi (2023)0.00