BGC：基于图聚类的多Agent群体信念
BGC: Multi-Agent Group Belief with Graph Clustering
摘要：
近年来，基于价值分解的多智能体强化学习方法在协调任务中取得了很好的效果。大多数现有的方法假设智能体可以进行通信以辅助决策，这在某些情况下是不切实际的。在本文中，我们提出了一种半通信的方法，使代理可以交换信息，而无需通信。具体来说，我们引入了一个组的概念，以帮助代理学习的信念，这是一种共识。有了这种共识，相邻的智能体倾向于完成类似的子任务，以实现合作。我们设计了一个新的代理结构命名为图聚类的信念（BGC），由一个代理的特征模块，一个信念模块，和一个融合模块。为了表示每个代理特征，我们使用基于MLP的特征模块来生成代理的唯一特征。受邻域认知一致性的启发，我们提出了一个基于组的模块，将相邻的智能体划分为一个小组，并最小化组内智能体的信念，以完成类似的子任务。最后，我们使用一个超网络合并这些功能，并产生代理的行动。为了克服GAT带来的Agent一致性问题，引入了一种分割损失来区分不同的Agent。结果表明，该方法取得了显着的改善，在SMAC基准。由于组的概念，我们的方法保持良好的性能与代理数量的增加。
英文摘要：
Recent advances have witnessed that value decomposed-based multi-agent reinforcement learning methods make an efficient performance in coordination tasks. Most current methods assume that agents can make communication to assist decisions, which is impractical in some situations. In this paper, we propose a semi-communication method to enable agents can exchange information without communication. Specifically, we introduce a group concept to help agents learning a belief which is a type of consensus. With this consensus, adjacent agents tend to accomplish similar sub-tasks to achieve cooperation. We design a novel agent structure named Belief in Graph Clustering(BGC), composed of an agent characteristic module, a belief module, and a fusion module. To represent each agent characteristic, we use an MLP-based characteristic module to generate agent unique features. Inspired by the neighborhood cognitive consistency, we propose a group-based module to divide adjacent agents into a small group and minimize in-group agents' beliefs to accomplish similar sub-tasks. Finally, we use a hyper-network to merge these features and produce agent actions. To overcome the agent consistent problem brought by GAT, a split loss is introduced to distinguish different agents. Results reveal that the proposed method achieves a significant improvement in the SMAC benchmark. Because of the group concept, our approach maintains excellent performance with an increase in the number of agents.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
