Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination

Abstract

Zero-shot coordination (ZSC), the ability to adapt to a new partner in a cooperative task, is a critical component of human-compatible AI. While prior work has focused on training agents to cooperate on a single task, these specialized models do not generalize to new tasks, even if they are highly similar. Here, we study how reinforcement learning on a distribution of environments with a single partner enables learning general cooperative skills that support ZSC with many new partners on many new problems. We introduce two Jax-based, procedural generators that create billions of solvable coordination challenges. We develop a new paradigm called Cross-Environment Cooperation (CEC), and show that it outperforms competitive baselines quantitatively and qualitatively when collaborating with real people. Our findings suggest that learning to collaborate across many unique scenarios encourages agents to develop general norms, which prove effective for collaboration with different partners. T

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyjha2025cross

Related papers

• Heterogeneous Multi-agent Zero-shot Coordination By Coevolution (2022)5.24
• Tackling Cooperative Incompatibility For Zero-shot Human-ai Coordination (2023)0.00
• Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In The Game Of Hanabi (2023)0.00
• Knowpc: Knowledge-driven Programmatic Reinforcement Learning For Zero-shot Coordination (2024)0.00
• Zero Shot Coordination For Sparse Reward Tasks With Diverse Reward Shapings (2026)0.00
• Noisy Zero-shot Coordination: Breaking The Common Knowledge Assumption In Zero-shot Coordination Games (2024)0.00
• Efficient Generation Of Diverse Cooperative Agents With World Models (2025)0.00
• Cooperative Open-ended Learning Framework For Zero-shot Coordination (2023)0.00