ESP: 対称性事前知識を活用したマルチエージェント強化学習
ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning
マルチエージェント系の対称性を事前知識としてデータ拡張と整合性損失に組み込み、既存のMARLアルゴリズムに適用可能なモデル非依存フレームワークを提案し、実機マルチロボットでも有効性を示した。
著者: Xin Yu, Rongye Shi, Pu Feng, Yongkai Tian, Jie Luo, Wenjun Wu
分類: cs.MA, cs.AI, cs.LG, cs.RO
原文アブストラクト
Multi-agent reinforcement learning (MARL) has achieved promising results in recent years. However, most existing reinforcement learning methods require a large amount of data for model training. In addition, data-efficient reinforcement learning requires the construction of strong inductive biases, which are ignored in the current MARL approaches. Inspired by the symmetry phenomenon in multi-agent systems, this paper proposes a framework for exploiting prior knowledge by integrating data augmentation and a well-designed consistency loss into the existing MARL methods. In addition, the proposed framework is model-agnostic and can be applied to most of the current MARL algorithms. Experimental tests on multiple challenging tasks demonstrate the effectiveness of the proposed framework. Moreover, the proposed framework is applied to a physical multi-robot testbed to show its superiority.
