局所正準化同変グラフニューラルネットワークによるサンプル効率と汎化性に優れた群ロボット制御
Local-Canonicalization Equivariant Graph Neural Networks for Sample-Efficient and Generalizable Swarm Robot Control
エージェント中心の正準化と役割認識グラフ符号化を組み合わせたモジュラーな方策アーキテクチャLEGOを提案し、MAPPOと組み合わせることで群ロボット制御のサンプル効率と未知チームサイズへの汎化を改善した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Keqin Wang, Tao Zhong, David Chang, Christine Allen-Blanchette
分類: cs.RO
原文アブストラクト
Multi-agent reinforcement learning (MARL) policies for swarm control often learn inefficiently and generalize poorly across coordinate frames, team sizes, and agent roles. We introduce Local-Canonicalization Equivariant Graph Neural Networks (LEGO), a modular policy architecture that combines agent-centric canonicalization with role-aware graph encoding. Canonicalization removes dependence on the global coordinate frame, while transforming predicted local actions back to the world frame produces an E(2)-equivariant policy. Role-wise graph encoders provide intra-role permutation equivariance and fixed-dimensional representations for variable-size teams. LEGO can be paired with standard MARL algorithms; we instantiate it with MAPPO. Across cooperative MPE Spread and competitive Tag-occlusion benchmarks, LEGO-MAPPO improves sample efficiency and task performance relative to MLP-based, graph-only, canonicalization-only, and equivariant baselines. The learned policies transfer without fine-tuning to unseen team sizes, maintain performance under spatial distribution shifts, and benefit from curriculum initialization for larger teams. In Crazyflie experiments, the policy remains operational after one pursuer is disabled. Code is available at https://github.com/CAB-Lab-Princeton/LEGO-MARL.
