多智能体通信中基于推理的确定性消息传递
Inference-Based Deterministic Messaging For Multi-Agent Communication
摘要：
沟通对于人类和动物之间的协调至关重要。因此，随着智能代理的引入，代理与代理以及代理与人之间的通信变得必要。在本文中，我们首先研究了基于矩阵的信号博弈中的学习，以实证的方式证明分散的方法可以收敛到一个次优的策略。然后，我们提出了一个修改的消息传递策略，其中发送者确定性地选择最好的消息，帮助接收者推断发送者的观察。使用这种修改，我们看到，经验，代理收敛到最优策略，在几乎所有的运行。然后，我们将这种方法应用到一个部分可观察的网格世界环境中，需要两个代理之间的合作，并表明，适当的近似方法，建议的发送者修改可以增强现有的分散训练方法，更复杂的域以及。
英文摘要：
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.
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。
