Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Chenxu, Jin, Yonggang, Hu, Cheng, Zhao, Youpeng, Dai, Zipeng, Zhao, Jian, Huang, Shiyu, Xiang, Liuyu, Zhang, Junge, He, Zhaofeng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915352785453056
author Wang, Chenxu
Jin, Yonggang
Hu, Cheng
Zhao, Youpeng
Dai, Zipeng
Zhao, Jian
Huang, Shiyu
Xiang, Liuyu
Zhang, Junge
He, Zhaofeng
author_facet Wang, Chenxu
Jin, Yonggang
Hu, Cheng
Zhao, Youpeng
Dai, Zipeng
Zhao, Jian
Huang, Shiyu
Xiang, Liuyu
Zhang, Junge
He, Zhaofeng
contents Adapting a single agent to a new multi-agent system brings challenges, necessitating adjustments across various tasks, environments, and interactions with unknown teammates and opponents. Addressing this challenge is highly complex, and researchers have proposed two simplified scenarios, Multi-agent reinforcement learning for zero-shot learning and Ad-Hoc Teamwork. Building on these foundations, we propose a more comprehensive setting, Agent Collaborative-Competitive Adaptation (ACCA), which evaluates an agent to generalize across diverse scenarios, tasks, and interactions with both unfamiliar opponents and teammates. In ACCA, agents adjust to task and environmental changes, collaborate with unseen teammates, and compete against unknown opponents. We introduce a new modeling approach, Multi-Retrieval and Dynamic Generation (MRDG), that effectively models both teammates and opponents using their behavioral trajectories. This method incorporates a positional encoder for varying team sizes and a hypernetwork module to boost agents' learning and adaptive capabilities. Additionally, a viewpoint alignment module harmonizes the observational perspectives of retrieved teammates and opponents with the learning agent. Extensive tests in benchmark scenarios like SMAC, Overcooked-AI, and Melting Pot show that MRDG significantly improves robust collaboration and competition with unseen teammates and opponents, surpassing established baselines. Our code is available at: https://github.com/vcis-wangchenxu/MRDG.git
format Preprint
id arxiv_https___arxiv_org_abs_2506_16718
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation
Wang, Chenxu
Jin, Yonggang
Hu, Cheng
Zhao, Youpeng
Dai, Zipeng
Zhao, Jian
Huang, Shiyu
Xiang, Liuyu
Zhang, Junge
He, Zhaofeng
Multiagent Systems
Artificial Intelligence
Adapting a single agent to a new multi-agent system brings challenges, necessitating adjustments across various tasks, environments, and interactions with unknown teammates and opponents. Addressing this challenge is highly complex, and researchers have proposed two simplified scenarios, Multi-agent reinforcement learning for zero-shot learning and Ad-Hoc Teamwork. Building on these foundations, we propose a more comprehensive setting, Agent Collaborative-Competitive Adaptation (ACCA), which evaluates an agent to generalize across diverse scenarios, tasks, and interactions with both unfamiliar opponents and teammates. In ACCA, agents adjust to task and environmental changes, collaborate with unseen teammates, and compete against unknown opponents. We introduce a new modeling approach, Multi-Retrieval and Dynamic Generation (MRDG), that effectively models both teammates and opponents using their behavioral trajectories. This method incorporates a positional encoder for varying team sizes and a hypernetwork module to boost agents' learning and adaptive capabilities. Additionally, a viewpoint alignment module harmonizes the observational perspectives of retrieved teammates and opponents with the learning agent. Extensive tests in benchmark scenarios like SMAC, Overcooked-AI, and Melting Pot show that MRDG significantly improves robust collaboration and competition with unseen teammates and opponents, surpassing established baselines. Our code is available at: https://github.com/vcis-wangchenxu/MRDG.git
title Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation
topic Multiagent Systems
Artificial Intelligence
url https://arxiv.org/abs/2506.16718