用深度分布式递归Q网络学习交流解谜
Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks
摘要：
我们提出了深度分布式递归Q网络（DDRQN），它使代理团队能够学习解决基于通信的协调任务。在这些任务中，代理没有任何预先设计的通信协议。因此，为了成功地进行通信，它们必须首先自动开发并商定自己的通信协议。我们提出了两个多智能体学习问题的经验结果的基础上著名的谜语，表明DDRQN可以成功地解决这些任务，并发现优雅的通信协议这样做。据我们所知，这是深度强化学习首次成功学习通信协议。此外，我们提出的消融实验，确认DDRQN架构的每个主要组成部分是其成功的关键。
英文摘要：
We propose deep distributed recurrent Q-networks (DDRQN), which enable teams of agents to learn to solve communication-based coordination tasks. In these tasks, the agents are not given any pre-designed communication protocol. Therefore, in order to successfully communicate, they must first automatically develop and agree upon their own communication protocol. We present empirical results on two multi-agent learning problems based on well-known riddles, demonstrating that DDRQN can successfully solve such tasks and discover elegant communication protocols to do so. To our knowledge, this is the first time deep reinforcement learning has succeeded in learning communication protocols. In addition, we present ablation experiments that confirm that each of the main components of the DDRQN architecture are critical to its success.
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。
