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 2203.03344cs.AI
收藏

基于对比学习的分布式多智能体通信

Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learning

Zebra Technologies(斑马技术公司)

Yat Long Lo, Biswa Sengupta

摘要:

为了成功地进行通信,代理之间需要一种共同的语言来理解彼此传达的信息。诱导共同语言的出现一直是多智能体学习系统面临的一个困难挑战。在这项工作中,我们引入了另一种观点,代理之间发送的通信消息,考虑他们作为不同的不完整的环境状态的意见。基于这一观点,我们提出了一个简单的方法来诱导一个共同的语言的出现,通过最大化的互信息之间的消息的一个给定的轨迹在一个自我监督的方式。通过在通信环境中评估我们的方法,我们经验性地展示了我们的方法如何导致更好的学习性能和速度,并学习比现有方法更一致的通用语言,而无需引入额外的学习参数。

英文摘要:

For communication to happen successfully, a common language is required between agents to understand information communicated by one another. Inducing the emergence of a common language has been a difficult challenge to multi-agent learning systems. In this work, we introduce an alternative perspective to the communicative messages sent between agents, considering them as different incomplete views of the environment state. Based on this perspective, we propose a simple approach to induce the emergence of a common language by maximizing the mutual information between messages of a given trajectory in a self-supervised manner. By evaluating our method in communication-essential environments, we empirically show how our method leads to better learning performance and speed, and learns a more consistent common language than existing methods, without introducing additional learning parameters.

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。

↑