用可解释的注意力机制让多智能体学会人类能懂的协作语言
Interpretable Emergent Language Using Inter-Agent Transformers
- 基于自注意力设计可解释的智能体通信架构
- 在合作任务中生成可理解的词汇与语义嵌入
- 适合需要透明决策过程的复杂多智能体系统
本文研究在多智能体强化学习（MARL）中使用Transformer实现语言涌现。现有方法如RIAL、DIAL和CommNet虽支持智能体间通信，但缺乏可解释性。我们提出可微分的智能体间Transformer（DIAT），利用自注意力机制学习符号化且人类可理解的通信协议。实验表明，DIAT能够将观测编码为可解释的词汇与有意义的嵌入，有效完成合作任务。结果表明DIAT在复杂多智能体环境中具备可解释通信的潜力。
原文摘要 · Abstract (English)
This paper explores the emergence of language in multi-agent reinforcement learning (MARL) using transformers. Existing methods such as RIAL, DIAL, and CommNet enable agent communication but lack interpretability. We propose Differentiable Inter-Agent Transformers (DIAT), which leverage self-attention to learn symbolic, human-understandable communication protocols. Through experiments, DIAT demonstrates the ability to encode observations into interpretable vocabularies and meaningful embeddings, effectively solving cooperative tasks. These results highlight the potential of DIAT for interpretable communication in complex multi-agent environments.
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。