通过学习通信内容实现多智能体策略的去中心化
Decentralization of Multiagent Policies by Learning What to Communicate
摘要：
机器人团队需要有效的沟通来解决复杂的协作任务。在实践中，通常由专家手动定义通信的编码和语义;无论行为本身是定制的、基于优化的还是学习的，都是如此。我们提出了一种代理体系结构和训练方法，基于通信未知专家策略的示例，使用神经网络来学习面向任务的通信语义。周边防御游戏说明了系统的能力，以处理动态变化的代理数量和其优雅的性能退化的通信约束收紧或专家的可观察性假设被打破。
英文摘要：
Effective communication is required for teams of robots to solve sophisticated collaborative tasks. In practice it is typical for both the encoding and semantics of communication to be manually defined by an expert; this is true regardless of whether the behaviors themselves are bespoke, optimization based, or learned. We present an agent architecture and training methodology using neural networks to learn task-oriented communication semantics based on the example of a communication-unaware expert policy. A perimeter defense game illustrates the system's ability to handle dynamically changing numbers of agents and its graceful degradation in performance as communication constraints are tightened or the expert's observability assumptions are broken.
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。
