意味空間における創発的な離散コミュニケーション
Emergent Discrete Communication in Semantic Spaces
強化学習エージェントが学習した連続空間から離散トークンを生成して通信する手法を提案し、意味的にクラスタ化されたトークンによりノイズ環境や未知の人間通信への対応が向上することを示した。
著者: Mycal Tucker, Huao Li, Siddharth Agrawal, Dana Hughes, Katia Sycara, Michael Lewis, Julie Shah
分類: cs.LG, cs.CL, cs.MA, cs.RO
原文アブストラクト
Neural agents trained in reinforcement learning settings can learn to communicate among themselves via discrete tokens, accomplishing as a team what agents would be unable to do alone. However, the current standard of using one-hot vectors as discrete communication tokens prevents agents from acquiring more desirable aspects of communication such as zero-shot understanding. Inspired by word embedding techniques from natural language processing, we propose neural agent architectures that enables them to communicate via discrete tokens derived from a learned, continuous space. We show in a decision theoretic framework that our technique optimizes communication over a wide range of scenarios, whereas one-hot tokens are only optimal under restrictive assumptions. In self-play experiments, we validate that our trained agents learn to cluster tokens in semantically-meaningful ways, allowing them communicate in noisy environments where other techniques fail. Lastly, we demonstrate both that agents using our method can effectively respond to novel human communication and that humans can understand unlabeled emergent agent communication, outperforming the use of one-hot communication.
関連論文
- 創発か帯域か:物理的結合と学習型マルチエージェント通信の限界マルチエージェント通信
