当前位置: X-MOL 学术arXiv.cs.MA › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Inference-Based Deterministic Messaging For Multi-Agent Communication
arXiv - CS - Multiagent Systems Pub Date : 2021-03-03 , DOI: arxiv-2103.02150
Varun Bhatt, Michael Buro

Communication is essential for coordination among humans and animals. Therefore, with the introduction of intelligent agents into the world, agent-to-agent and agent-to-human communication becomes necessary. In this paper, we first study learning in matrix-based signaling games to empirically show that decentralized methods can converge to a suboptimal policy. We then propose a modification to the messaging policy, in which the sender deterministically chooses the best message that helps the receiver to infer the sender's observation. Using this modification, we see, empirically, that the agents converge to the optimal policy in nearly all the runs. We then apply this method to a partially observable gridworld environment which requires cooperation between two agents and show that, with appropriate approximation methods, the proposed sender modification can enhance existing decentralized training methods for more complex domains as well.

中文翻译:

基于推理的多主体通信确定性消息传递

交流对于人与动物之间的协调至关重要。因此,随着智能代理的引入,代理到代理和代理到人之间的通信成为必要。在本文中,我们首先研究基于矩阵的信号博弈中的学习,以经验表明分散方法可以收敛于次优策略。然后,我们提出对消息传递策略的修改,其中,发送方确定地选择最佳消息,以帮助接收方推断出发送方的观察结果。使用此修改,从经验上我们可以看到,代理几乎在所有运行中都收敛于最佳策略。然后,我们将此方法应用于部分可观察到的Gridworld环境,该环境需要两个代理之间的协作,并证明使用适当的近似方法,
更新日期:2021-03-04
down
wechat
bug