対称性を強化したマルチエージェント強化学習
Symmetries-enhanced Multi-Agent Reinforcement Learning
マルチエージェント系に外在的な対称性を埋め込む枠組みを提案し、群れロボットの衝突低減とタスク成功率向上を実現した。
著者: Nikolaos Bousias, Stefanos Pertigkiozoglou, Kostas Daniilidis, George Pappas
分類: cs.RO, cs.AI, cs.LG, cs.MA, math.RT
原文アブストラクト
Multi-agent reinforcement learning has emerged as a powerful framework for enabling agents to learn complex, coordinated behaviors but faces persistent challenges regarding its generalization, scalability and sample efficiency. Recent advancements have sought to alleviate those issues by embedding intrinsic symmetries of the systems in the policy. Yet, most dynamical systems exhibit little to no symmetries to exploit. This paper presents a novel framework for embedding extrinsic symmetries in multi-agent system dynamics that enables the use of symmetry-enhanced methods to address systems with insufficient intrinsic symmetries, expanding the scope of equivariant learning to a wide variety of MARL problems. Central to our framework is the Group Equivariant Graphormer, a group-modular architecture specifically designed for distributed swarming tasks. Extensive experiments on a swarm of symmetry-breaking quadrotors validate the effectiveness of our approach, showcasing its potential for improved generalization and zero-shot scalability. Our method achieves significant reductions in collision rates and enhances task success rates across a diverse range of scenarios and varying swarm sizes.
