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 2511.03348cs.MA
收藏

多任务多智能体深度强化学习中的通信技能学习

Learning Communication Skills in Multi-task Multi-agent Deep Reinforcement Learning

Utrecht University(乌得勒支大学)

Changxi Zhu, Mehdi Dastani, Shihan Wang

AI总结:

本文提出多任务通信技能(MCS)方法,通过Transformer编码器和预测网络学习共享通信协议,使多智能体能同时执行多个任务,并在多任务基准实验中优于无通信多任务基线及单任务基线。

摘要:

在多智能体深度强化学习(MADRL)中,智能体可以通过相互通信以协调方式执行任务。当涉及多个任务时,智能体还可以利用来自一个任务的知识来改善在其他任务中的学习。在本文中,我们提出了多任务通信技能(MCS),这是一种具有通信能力的MADRL方法,能够同时学习和执行多个任务,智能体通过可学习的通信协议进行交互。MCS采用Transformer编码器将特定于任务的观测编码到共享消息空间中,从而捕获智能体之间共享的通信技能。为了增强智能体之间的协调性,我们引入了一个预测网络,将消息与每个任务中发送方智能体的动作相关联。我们将三个多智能体基准环境适配到多任务设置中,在这些设置中,智能体的数量以及观测空间和动作空间在不同任务之间有所不同。实验结果表明,与没有通信的多任务MADRL基线以及有通信和没有通信的单任务MADRL基线相比,MCS取得了更好的性能。

英文摘要:

In multi-agent deep reinforcement learning (MADRL), agents can communicate with one another to perform a task in a coordinated manner. When multiple tasks are involved, agents can also leverage knowledge from one task to improve learning in other tasks. In this paper, we propose Multi-task Communication Skills (MCS), a MADRL with communication method that learns and performs multiple tasks simultaneously, with agents interacting through learnable communication protocols. MCS employs a Transformer encoder to encode task-specific observations into a shared message space, capturing shared communication skills among agents. To enhance coordination among agents, we introduce a prediction network that correlates messages with the actions of sender agents in each task. We adapt three multi-agent benchmark environments to multi-task settings, where the number of agents as well as the observation and action spaces vary across tasks. Experimental results demonstrate that MCS achieves better performance than multi-task MADRL baselines without communication, as well as single-task MADRL baselines with and without communication.

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。

↑