Shaping Zero-Shot Coordination via State Blocking
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 36 of its 54 references that are in the map. First posted on arXiv 12 May 2026.
Builds on
36 of 54 references.
References · 36
- 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
- 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,241
- 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
- 2018Exploration by Random Network Distillationcited by 993
- 2017Constrained Policy Optimizationcited by 983
- 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
- 2020MOPO: Model-based Offline Policy Optimizationcited by 636
- 2020MOReL : Model-Based Offline Reinforcement Learningcited by 590
- 2018Reward Constrained Policy Optimizationcited by 417
- 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
- 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 316
- 2016#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learningcited by 309
24 more
- 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 294
- 2018Large-Scale Study of Curiosity-Driven Learningcited by 280
- 2017Count-Based Exploration with Neural Density Modelscited by 257
- 2020Projection-Based Constrained Policy Optimizationcited by 203
- 2020"Other-Play" for Zero-Shot Coordinationcited by 198
- 2019The Hanabi Challenge: A New Frontier for AI Researchcited by 197
- 2021Collaborating with Humans without Human Datacited by 142
- 2020Watch-And-Help: A Challenge for Social Perception and Human-AI Collaborationcited by 133
- 2021Off-Belief Learningcited by 75
- 2021Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordinationcited by 70
- 2023JaxMARL: Multi-Agent RL Environments and Algorithms in JAXcited by 63
- 2020Towards Open Ad Hoc Teamwork Using Graph-based Policy Learningcited by 37
- 2021A New Formalism, Method and Open Issues for Zero-Shot Coordinationcited by 33
- 2022K-level Reasoning for Zero-Shot Coordination in Hanabicited by 32
- 2019Controlling Assistive Robots with Learned Latent Actionscited by 28
- 2024Learning to Cooperate with Humans using Generative Agentscited by 24
- 2022Any-Play: An Intrinsic Augmentation for Zero-Shot Coordinationcited by 23
- 2024Human-compatible driving partners through data-regularized self-play reinforcement learningcited by 17
- 2022Equivariant Networks for Zero-Shot Coordinationcited by 16
- 2024N-Agent Ad Hoc Teamworkcited by 15
- 2022Coordination with Humans via Strategy Matchingcited by 14
- 2025Cross-environment Cooperation Enables Zero-shot Multi-agent Coordinationcited by 14
- 2021Adaptable Agent Populations via a Generative Model of Policiescited by 12
- 2025Adaptively Coordinating with Novel Partners via Learned Latent Strategiescited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.