Cooperative Open-ended Learning Framework for Zero-shot Coordination

Yang Li, Shao Zhang, Jichen Sun, Yali Du, Ying Wen, Xinbing Wang, Wei Pan

Research output: Contribution to journalConference articlepeer-review

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 overcome cooperative incompatibility. The experimental results in the Overcooked game environment demonstrate that our method outperforms current state-of-the-art methods when coordinating with different-level partners. Our demo is available at https://sites.google.com/view/cole-2023/.

Original languageEnglish
Pages (from-to)19837-19854
Number of pages18
JournalProceedings of Machine Learning Research
Volume202
Publication statusPublished - 2023
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: 23 Jul 202329 Jul 2023

Fingerprint

Dive into the research topics of 'Cooperative Open-ended Learning Framework for Zero-shot Coordination'. Together they form a unique fingerprint.

Cite this