论文标题
在合作多机构增强学习中学习实用的交流策略
Learning Practical Communication Strategies in Cooperative Multi-Agent Reinforcement Learning
论文作者
论文摘要
在多机构强化学习中，沟通对于鼓励代理商之间的合作至关重要。由于网络条件随着代理的移动性而变化，并且在传输过程中的随机性变化，因此现实的无线网络中的通信可能非常不可靠。我们提出了一个框架来通过解决三个基本问题来学习实用的沟通策略：（1）何时：代理商不仅基于消息重要性，而且是无线渠道条件来学习沟通的时间。 （2）什么：用无线网络测量值的代理增强消息内容，以更好地选择游戏和通信操作。 （3）如何：代理使用新颖的神经信息编码器来保留从接收到的消息中的所有信息，无论消息的数量和顺序如何。与最先进的面前相比，在逼真的无线网络设置下模拟标准基准测试，我们在游戏性能，收敛速度和沟通效率方面取得了重大改进。
In Multi-Agent Reinforcement Learning, communication is critical to encourage cooperation among agents. Communication in realistic wireless networks can be highly unreliable due to network conditions varying with agents' mobility, and stochasticity in the transmission process. We propose a framework to learn practical communication strategies by addressing three fundamental questions: (1) When: Agents learn the timing of communication based on not only message importance but also wireless channel conditions. (2) What: Agents augment message contents with wireless network measurements to better select the game and communication actions. (3) How: Agents use a novel neural message encoder to preserve all information from received messages, regardless of the number and order of messages. Simulating standard benchmarks under realistic wireless network settings, we show significant improvements in game performance, convergence speed and communication efficiency compared with state-of-the-art.
