arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.04740cs.LGcs.MA
收藏

多智能体强化学习中的图卷积值分解

Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning

HRL Laboratories, LLC(HRL实验室有限责任公司)

Navid Naderializadeh, Fan H. Hung, Sean Soleyman, Deepak Khosla

摘要:

我们提出了一种新的框架,用于多智能体深度强化学习(MARL)中的价值函数分解,使用图神经网络(GNNs)。特别是,我们认为团队的代理作为一个完整的有向图,其边的权重是由一个注意力机制的节点集。在这个基础图的基础上,我们引入了一个混合GNN模块,它负责i)将团队状态-动作价值函数分解为各个代理的观察-动作价值函数,以及ii)根据全局团队奖励的分数向每个代理显式分配信用分配。我们称之为GraphMIX的方法遵循集中式训练和分散式执行范式,使代理能够在训练完成后独立做出决策。我们展示了GraphMIX在星际争霸II多智能体挑战(SMAC)基准测试中的几个场景中的优越性。我们进一步展示了GraphMIX如何与最近的分层MARL架构结合使用,以提高代理的性能,并在具有更多代理和/或动作的不匹配测试场景中对其进行微调。

英文摘要:

We propose a novel framework for value function factorization in multi-agent deep reinforcement learning (MARL) using graph neural networks (GNNs). In particular, we consider the team of agents as the set of nodes of a complete directed graph, whose edge weights are governed by an attention mechanism. Building upon this underlying graph, we introduce a mixing GNN module, which is responsible for i) factorizing the team state-action value function into individual per-agent observation-action value functions, and ii) explicit credit assignment to each agent in terms of fractions of the global team reward. Our approach, which we call GraphMIX, follows the centralized training and decentralized execution paradigm, enabling the agents to make their decisions independently once training is completed. We show the superiority of GraphMIX as compared to the state-of-the-art on several scenarios in the StarCraft II multi-agent challenge (SMAC) benchmark. We further demonstrate how GraphMIX can be used in conjunction with a recent hierarchical MARL architecture to both improve the agents' performance and enable fine-tuning them on mismatched test scenarios with higher numbers of agents and/or actions.

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。

↑