Learning to Communicate: A Machine Learning Framework for Heterogeneous Multi-Agent Robotic Systems
Learning to Communicate: A Machine Learning Framework for Heterogeneous Multi-Agent Robotic Systems
复制标题
DOI：
10.2514/6.2019-1456
复制
发表时间：
2018-12
期刊：
影响因子：
--
通讯作者：
Hyung-Jin Yoon;Huaiyu Chen;Kehan Long;Heling Zhang;Aditya Gahlawat;Donghwan Lee;N. Hovakimyan
中科院分区：
文献类型：
--
作者：
Hyung-Jin Yoon;Huaiyu Chen;Kehan Long;Heling Zhang;Aditya Gahlawat;Donghwan Lee;N. Hovakimyan
我们提出了一个机器学习框架，多智能体系统学习的最佳策略，最大化的奖励和编码的高维视觉观察。该编码对于在通信资源约束下与其他代理共享本地视觉观察是有用的。Actor编码器对原始图像进行编码，并根据本地观察和其他代理发送的消息选择动作。机器学习代理不仅生成对物理设备的致动器命令，还生成对其他代理的通信消息。我们制定了一个强化学习问题，它扩展了行动空间，以考虑通信行动。强化学习框架的可行性证明了使用3D仿真环境与两个合作代理。该环境提供了两个代理之间使用和共享的逼真的视觉观察。
We present a machine learning framework for multi-agent systems to learn both the optimal policy for maximizing the rewards and the encoding of the high dimensional visual observation. The encoding is useful for sharing local visual observations with other agents under communication resource constraints. The actor-encoder encodes the raw images and chooses an action based on local observations and messages sent by the other agents. The machine learning agent generates not only an actuator command to the physical device, but also a communication message to the other agents. We formulate a reinforcement learning problem, which extends the action space to consider the communication action as well. The feasibility of the reinforcement learning framework is demonstrated using a 3D simulation environment with two collaborating agents. The environment provides realistic visual observations to be used and shared between the two agents.