Scholarlink

<p>Symmetry is prevalent in multi-agent systems. The presence of symmetry, coupled with the misuse of absolute coordinate systems, often leads to a large amount of redundant representation space, significantly increasing the search space for learning policies and reducing learning efficiency. Effectively utilizing symmetry and extracting symmetry-invariant representations can significantly enhance multi-agent systems’ learning efficiency and overall performance by compressing the model’s hypothesis space and improving sample efficiency. The issue of rotational symmetry in multi-agent reinforcement learning has received little attention in previous research and is the primary focus of this paper. To address this issue, we propose a rotation-invariant network architecture for continuous action space tasks. This architecture utilizes relative coordinates between agents, eliminating dependence on absolute coordinate systems, and employs a hypernetwork to enhance the model’s fitting capability, enabling it to model MDPs with more complex dynamics. It can be used for both predicting actions and evaluating action values/utilities. In benchmark tasks, experimental results validate the impact of rotational symmetry on multi-agent decision systems and demonstrate the effectiveness of our method. The code of RDHNet has been available at the website of <a href="https://github.com/wang88256187/RDHNet">github.com/wang88256187/RDHNet</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

RDHNet: addressing rotational and permutational symmetries in continuous multi-agent systems

  • 期刊论文

  • 发表日期：

    2025年4月3日

查看全文
  • Dongzi Wang,
  • Lilan Huang,
  • Muning Wen,
  • Yuanxi Peng,
  • Minglong Li,
  • Teng Li

摘要

Symmetry is prevalent in multi-agent systems. The presence of symmetry, coupled with the misuse of absolute coordinate systems, often leads to a large amount of redundant representation space, significantly increasing the search space for learning policies and reducing learning efficiency. Effectively utilizing symmetry and extracting symmetry-invariant representations can significantly enhance multi-agent systems’ learning efficiency and overall performance by compressing the model’s hypothesis space and improving sample efficiency. The issue of rotational symmetry in multi-agent reinforcement learning has received little attention in previous research and is the primary focus of this paper. To address this issue, we propose a rotation-invariant network architecture for continuous action space tasks. This architecture utilizes relative coordinates between agents, eliminating dependence on absolute coordinate systems, and employs a hypernetwork to enhance the model’s fitting capability, enabling it to model MDPs with more complex dynamics. It can be used for both predicting actions and evaluating action values/utilities. In benchmark tasks, experimental results validate the impact of rotational symmetry on multi-agent decision systems and demonstrate the effectiveness of our method. The code of RDHNet has been available at the website of github.com/wang88256187/RDHNet.