CooT: Learning to Coordinate In-Context with Coordination Transformers
- URL: http://arxiv.org/abs/2506.23549v1
- Date: Mon, 30 Jun 2025 06:45:39 GMT
- Title: CooT: Learning to Coordinate In-Context with Coordination Transformers
- Authors: Huai-Chih Wang, Hsiang-Chun Chuang, Hsi-Chun Cheng, Dai-Jie Wu, Shao-Hua Sun,
- Abstract summary: Coordination Transformers (CooT) is a novel in-context coordination framework that uses recent interaction histories to adapt to unseen partners rapidly.<n>Trained on interaction trajectories collected from diverse pairs of agents, CooT quickly learns effective coordination strategies without explicit supervision or fine-tuning.<n>Human evaluations confirm CooT as the most effective collaborative partner, while extensive ablations highlight its robustness, flexibility, and sensitivity to context in multi-agent scenarios.
- Score: 4.205946699819021
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Effective coordination among artificial agents in dynamic and uncertain environments remains a significant challenge in multi-agent systems. Existing approaches, such as self-play and population-based methods, either generalize poorly to unseen partners or require extensive training. To overcome these limitations, we propose Coordination Transformers (CooT), a novel in-context coordination framework that uses recent interaction histories to adapt to unseen partners rapidly. Unlike previous approaches that primarily aim to increase the diversity of training partners, CooT explicitly focuses on adapting to new partner behaviors by predicting actions aligned with observed partner interactions. Trained on interaction trajectories collected from diverse pairs of agents with complementary behaviors, CooT quickly learns effective coordination strategies without explicit supervision or fine-tuning. Evaluations on the Overcooked benchmark demonstrate that CooT significantly outperforms baseline methods in coordination tasks involving previously unseen partners. Human evaluations further confirm CooT as the most effective collaborative partner, while extensive ablations highlight its robustness, flexibility, and sensitivity to context in multi-agent scenarios.
Related papers
- Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies [0.0]
Team-Attention-Actor-Critic (TAAC) is a learning algorithm designed to enhance multi-agent collaboration in cooperative environments.<n>We evaluate TAAC in a simulated soccer environment against benchmark algorithms.
arXiv Detail & Related papers (2025-07-30T15:48:38Z) - Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination [37.90912492084769]
We study how reinforcement learning on a distribution of environments with a single partner enables learning general cooperative skills.<n>We introduce two Jax-based, procedural generators that create billions of solvable coordination challenges.<n>Our findings suggest that learning to collaborate across many unique scenarios encourages agents to develop general norms.
arXiv Detail & Related papers (2025-04-17T07:41:25Z) - ProAgent: Building Proactive Cooperative Agents with Large Language
Models [89.53040828210945]
ProAgent is a novel framework that harnesses large language models to create proactive agents.
ProAgent can analyze the present state, and infer the intentions of teammates from observations.
ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
arXiv Detail & Related papers (2023-08-22T10:36:56Z) - Adaptive Coordination in Social Embodied Rearrangement [49.35582108902819]
We study zero-shot coordination (ZSC) in this task, where an agent collaborates with a new partner, emulating a scenario where a robot collaborates with a new human partner.
We propose Behavior Diversity Play (BDP), a novel ZSC approach that encourages diversity through a discriminability objective.
Our results demonstrate that BDP learns adaptive agents that can tackle visual coordination, and zero-shot generalize to new partners in unseen environments, achieving 35% higher success and 32% higher efficiency compared to baselines.
arXiv Detail & Related papers (2023-05-31T18:05:51Z) - PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI
Coordination [52.991211077362586]
We propose a policy ensemble method to increase the diversity of partners in the population.
We then develop a context-aware method enabling the ego agent to analyze and identify the partner's potential policy primitives.
In this way, the ego agent is able to learn more universal cooperative behaviors for collaborating with diverse partners.
arXiv Detail & Related papers (2023-01-16T12:14:58Z) - Cooperative guidance of multiple missiles: a hybrid co-evolutionary
approach [0.9176056742068814]
Cooperative guidance of multiple missiles is a challenging task with rigorous constraints of time and space consensus.
This paper develops a novel natural co-evolutionary strategy (NCES) to address the issues of non-stationarity and continuous control faced by cooperative guidance.
A hybrid co-evolutionary cooperative guidance law (HCCGL) is proposed by integrating the highly scalable co-evolutionary mechanism and the traditional guidance strategy.
arXiv Detail & Related papers (2022-08-15T12:59:38Z) - Depthwise Convolution for Multi-Agent Communication with Enhanced
Mean-Field Approximation [9.854975702211165]
We propose a new method based on local communication learning to tackle the multi-agent RL (MARL) challenge.
First, we design a new communication protocol that exploits the ability of depthwise convolution to efficiently extract local relations.
Second, we introduce the mean-field approximation into our method to reduce the scale of agent interactions.
arXiv Detail & Related papers (2022-03-06T07:42:43Z) - Conditional Imitation Learning for Multi-Agent Games [89.897635970366]
We study the problem of conditional multi-agent imitation learning, where we have access to joint trajectory demonstrations at training time.
We propose a novel approach to address the difficulties of scalability and data scarcity.
Our model learns a low-rank subspace over ego and partner agent strategies, then infers and adapts to a new partner strategy by interpolating in the subspace.
arXiv Detail & Related papers (2022-01-05T04:40:13Z) - Distributed Adaptive Learning Under Communication Constraints [54.22472738551687]
This work examines adaptive distributed learning strategies designed to operate under communication constraints.
We consider a network of agents that must solve an online optimization problem from continual observation of streaming data.
arXiv Detail & Related papers (2021-12-03T19:23:48Z) - On the Critical Role of Conventions in Adaptive Human-AI Collaboration [73.21967490610142]
We propose a learning framework that teases apart rule-dependent representation from convention-dependent representation.
We experimentally validate our approach on three collaborative tasks varying in complexity.
arXiv Detail & Related papers (2021-04-07T02:46:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.