.png){kind=icon}
返回
Coordinating Multi-Agent Reinforcement Learning via Dual Collaborative Constraints
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2024.106858.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Many real-world multi-agent tasks exhibit a nearly decomposable structure, where interactions among agents within the same interaction set are strong while interactions between different sets are relatively weak. Efficiently modeling the nearly decomposable structure and leveraging it to coordinate agents can enhance the learning efficiency of multi-agent reinforcement learning algorithms for cooperative tasks, while existing works typically fail. To overcome this limitation, this paper proposes a novel algorithm named Dual Collaborative Constraints (DCC) that identifies the interaction sets as subtasks and achieves both intra-subtask and intersubtask coordination. Specifically, DCC employs a bi-level structure to periodically distribute agents into multiple subtasks, and proposes both local and global collaborative constraints based on mutual information to facilitate both intra-subtask and inter-subtask coordination among agents. These two constraints ensure that agents within the same subtask reach a consensus on their local action selections and all of them select superior joint actions that maximize the overall task performance. Experimentally, we evaluate DCC on various cooperative multi-agent tasks, and its superior performance against multiple state-of-the-art baselines demonstrates its effectiveness.
Keyword:
Multi-agent reinforcement learning
Cooperative tasks
Coordination
Nearly decomposable structure
期刊
IF:
6.3
论文数:
7.8K
被引数:
3.0W
机构
引用论文
IHG-MA: Inductive heterogeneous graph multi-agent reinforcement learning for multi-intersection traffic signal controlIhg-ma: 用于多路口交通信号控制的归纳异构图多智能体强化学习.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏Decentralized control and local information for robust and adaptive decentralized Deep Reinforcement Learning用于鲁棒和自适应分散深度强化学习的分散控制和局部信息NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏分享收藏
Distributed deep reinforcement learning based on bi-objective framework for multi-robot formationNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏Defect-driven synthesis of self-assembled single crystal titanium nanowires via electrochemistry
PREAI
分享收藏
查看更多内容