不靠沟通，仅看动作就能高效协作。
Learning to Coordinate without Communication under Incomplete Information
- 通过观察对方动作序列推断意图，构建状态机策略
- 性能接近有沟通时的协作水平，远超无协调方案
- 适合通信受限的多智能体协同场景
在人工智能的协作游戏中，当参与者处于信息不完整的情况下实现无缝协调是一项关键挑战。尽管通信有助于解决该问题，但并非总是可行。本文探索了在无语言沟通条件下，仅通过观察彼此行为来实现有效协作的可能性。我们的方法使智能体能够将合作方的动作序列解读为意图信号，为每个可能采取的动作构建基于确定性有限自动机的有限状态转换器。实验表明，这些策略显著优于非协调方案，并且性能接近通过直接通信实现的协作水平。
原文摘要 · Abstract (English)
Achieving seamless coordination in cooperative games is a crucial challenge in artificial intelligence, particularly when players operate under incomplete information. While communication helps, it is not always feasible. In this paper, we explore how effective coordination can be achieved without verbal communication, relying solely on observing each other's actions. Our method enables an agent to develop a strategy by interpreting its partner's action sequences as intent signals, constructing a finite-state transducer built from deterministic finite automata, one for each possible action the agent can take. Experiments show that these strategies significantly outperform uncoordinated ones and closely match the performance of coordinating via direct communication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。