paper-with-me

홈 › Papers

Multi-agent Continual Coordination via Progressive Task Contextualization

2023-05-07 · Lei Yuan, Lihe Li, Ziqian Zhang, Fuxiang Zhang, Cong Guan, Yang Yu

Cooperative Multi-agent Reinforcement Learning (MARL) has attracted significant attention and played the potential for many real-world applications. Previous arts mainly focus on facilitating the coordination ability from different aspects (e.g., non-stationarity, credit assignment) in single-task or multi-task scenarios, ignoring the stream of tasks that appear in a continual manner. This ignorance makes the continual coordination an unexplored territory, neither in problem formulation nor efficient algorithms designed. Towards tackling the mentioned issue, this paper proposes an approach Multi-Agent Continual Coordination via Progressive Task Contextualization, dubbed MACPro. The key point lies in obtaining a factorized policy, using shared feature extraction layers but separated independent task heads, each specializing in a specific class of tasks. The task heads can be progressively expanded based on the learned task contextualization. Moreover, to cater to the popular CTDE paradigm in MARL, each agent learns to predict and adopt the most relevant policy head based on local information in a decentralized manner. We show in multiple multi-agent benchmarks that existing continual learning methods fail, while MACPro is able to achieve close-to-optimal performance. More results also disclose the effectiveness of MACPro from multiple aspects like high generalization ability.

📄 PDF Abstract BibTeX arXiv:2305.13937

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningMulti-agent Reinforcement Learning

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

Offline Multi-agent Continual Cooperation via Skill Partition and Reuse

2026-06-24 · Yuchen Xiao, Lei Yuan, Ruiqi Xue, Tieyue Yin 외 arxiv

Extracting skills from multi-agent offline dataset improves learning efficiency via sharing task-invariant coordination skills among tasks. In settings where tasks occur sequentially and the space of skills grows exponen…

HULK: Large-scale Hierarchical Coordination under Continual and Uncertain Temporal Tasks

2026-05-09 · Qingyuan Luo, Jie Li, Meng Guo arxiv

Multi-agent systems can be extremely efficient when working concurrently and collaboratively, e.g., for delivery, surveillance, search and rescue. Coordination of such teams often involves two aspects: selecting appropri…

Computational Efficiency

Continual Quadruped Robots Coordination via Semantic Skill Discovery

2026-06-06 · Daoqing Wang, Yuchen Xiao, Weixuan Huang, Zhilong Zhang 외 arxiv

Multi-quadruped coordination has attracted increasing attention due to its enhanced payload capacity, broader contact coverage, and improved adaptability to challenging tasks. Existing methods for multi-quadruped manipul…

Multi-agent Reinforcement LearningContinual Learning

Deep Reinforcement Learning for Multi-Agent Coordination

2025-10-04 · Kehinde O. Aina, Sehoon Ha arxiv

We address the challenge of coordinating multiple robots in narrow and confined environments, where congestion and interference often hinder collective task performance. Drawing inspiration from insect colonies, which ac…

Reinforcement Learning

AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems

2025-04-01 · Yingxuan Yang, Huacan Chai, Shuai Shao, Yuanyi Song 외

The rapid advancement of large language models (LLMs) has enabled the development of multi-agent systems where multiple LLM-based agents collaborate on complex tasks. However, existing systems often rely on centralized c…

Privacy PreservingRAGRetrievalRetrieval-augmented Generation