マルチエージェント方策の分散化：何を通信すべきかを学習する
Decentralization of Multiagent Policies by Learning What to Communicate
通信を前提としない専門家方策を例に、ニューラルネットワークでタスク指向の通信意味論を学習するエージェントアーキテクチャと訓練手法を提案し、周辺防衛ゲームで動的なエージェント数変化や通信制約下での性能劣化を実証した。
著者: James Paulos, Steven W. Chen, Daigo Shishika, Vijay Kumar
分類: cs.RO
原文アブストラクト
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.
