用局部轨迹建模其他智能体行为，提升多智能体系统决策效果。
TransAM: Transformer-Based Agent Modeling for Multi-Agent Systems via Local Trajectory Encoding
- 基于变压器架构，从自身轨迹学习其他智能体策略
- 在合作、竞争和混合环境中均提升策略表征能力
- 适合无法获取他人完整轨迹的真实场景应用
智能体建模是多智能体系统中制定有效策略的关键，使智能体能够推断其他智能体的行为、意图和能力。现有方法通常假设可访问其他智能体的完整轨迹，这一条件在现实应用中往往不成立。因此，实用的智能体建模方法必须仅基于受控智能体的局部轨迹来学习其他智能体策略的鲁棒表示。本文提出 exttt{TransAM}，一种基于变压器的新型智能体建模方法，通过编码局部轨迹生成嵌入空间，有效捕捉其他智能体的策略。我们在合作、竞争及混合多智能体环境中评估了该方法性能。大量实验结果表明，该方法生成了强大的策略表征，提升了智能体建模效果，并带来更高的累积回报。
原文摘要 · Abstract (English)
Agent modeling is a critical component in developing effective policies within multi-agent systems, as it enables agents to form beliefs about the behaviors, intentions, and competencies of others. Many existing approaches assume access to other agents' episodic trajectories, a condition often unrealistic in real-world applications. Consequently, a practical agent modeling approach must learn a robust representation of the policies of the other agents based only on the local trajectory of the controlled agent. In this paper, we propose \texttt{TransAM}, a novel transformer-based agent modeling approach to encode local trajectories into an embedding space that effectively captures the policies of other agents. We evaluate the performance of the proposed method in cooperative, competitive, and mixed multi-agent environments. Extensive experimental results demonstrate that our approach generates strong policy representations, improves agent modeling, and leads to higher episodic returns.
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。