Shaping Zero-Shot Coordination via State Blocking

2026-05-12

AI Summary

This work addresses the core challenge of zero-shot coordination—achieving reliable collaboration with partners without prior interaction—by proposing the State-Blocked Coordination (SBC) framework. SBC enhances an agent’s ability to generalize to unseen partners, including humans, by constructing virtual training environments in which specific states are systematically blocked to generate diverse, suboptimal partner behaviors. This approach increases policy diversity and robustness without altering the original environment, relying solely on a state-space restriction mechanism. Empirical results demonstrate that SBC significantly outperforms existing methods across multiple benchmark tasks and exhibits exceptional zero-shot coordination performance when collaborating with human partners.

Abstract

Zero-shot coordination (ZSC) aims to enable agents to cooperate with independently trained partners without prior interaction, a key requirement for real-world multi-agent systems and human-AI collaboration. Existing approaches have largely emphasized increasing partner diversity during training, yet such strategies often fall short of achieving reliable generalization to unseen partners. We introduce State-Blocked Coordination (SBC), a simple yet effective framework that improves ZSC by inducing diverse interaction scenarios without direct environment modification. Specifically, SBC generates a family of virtual environments through state blocking, allowing agents to experience a wide range of suboptimal partner policies. Across multiple benchmarks, SBC demonstrates superior performance in zero-shot coordination, including strong generalization to human partners.

Problem

• Zero-shot coordination
• multi-agent systems
• partner diversity
• generalization
• human-AI collaboration

Innovation

• Zero-Shot Coordination
• State Blocking
• Multi-Agent Systems
• Partner Generalization
• Virtual Environments