[2406.04219] Multi-Agent Imitation Learning: Value is Easy, Regret is Hard

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2406.04219] Multi-Agent Imitation Learning: Value is Easy, Regret is Hard --> Computer Science > Machine Learning arXiv:2406.04219 (cs) [Submitted on 6 Jun 2024 ( v1 ), last revised 26 Jun 2024 (this version, v2)] Title: Multi-Agent Imitation Learning: Value is Easy, Regret is Hard Authors: Jingwu Tang , Gokul Swamy , Fei Fang , Zhiwei Steven Wu View a PDF of the paper titled Multi-Agent Imitation Learning: Value is Easy, Regret is Hard, by Jingwu Tang and 3 other authors View PDF HTML (experimental) Abstract: We study a multi-agent imitation learning (MAIL) problem where we take the perspect

saved by

• Siddhant Sharma

related reading

• [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingarxiv.org
• [2512.18552] Toward Training Superintelligent Software Agents through Self-Play SWE-RLarxiv.org
• [2506.22401] Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RLarxiv.org
• [2502.14143] Multi-Agent Risks from Advanced AIarxiv.org
• [2406.11717] Refusal in Language Models Is Mediated by a Single Directionarxiv.org
• 1011.0686arxiv.org
• [2603.21972] Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipearxiv.org
• [2606.09758] Difference-Aware Retrieval Policies for Imitation Learningarxiv.org
• [2406.02061] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Modelsarxiv.org
• [2305.18784] Collaborative Multi-Agent Heterogeneous Multi-Armed Banditsarxiv.org
• [2301.08028] A Tutorial on Meta-Reinforcement Learningarxiv.org
• [2605.22748] Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learningarxiv.org