LooperMuscle: 構造化Mixture-of-Expertsによるヒューマノイド全身追従の高速かつ安定な学習
LooperMuscle: Fast and Stable Learning of Humanoid Whole-Body Tracking via Structured Mixture-of-Experts
ヒューマノイドの全身追従タスクにおいて、高速学習手法FastSACの性能低下を、構造化MoEアクターと専門家認識型クリティック、寄与度ルーティングリプレイを組み合わせた閉ループ学習で改善し、PPOに近い精度を約45分で達成した。
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: Boyi Liu, Qijin Li, Tianqi Yu, Qinrui Yan, Xingxing Zuo
分類: cs.RO
原文アブストラクト
FastSAC-style methods significantly reduce humanoid motion training time but often suffer from notable performance degradation compared with PPO in whole-body tracking tasks. We target this speed-performance gap by introducing LooperMuscle, a composed expert policy learning framework that restores tracking quality while preserving high training efficiency. LooperMuscle combines a semantically structured mixture-of-experts actor, an expert-aware distributional critic, and contribution-routed replay with deferred curriculum scheduling. These three components form a closed training loop in which expert contributions guide data routing, routed data shape value learning, and value gradients in turn refine expert specialization. Empirically, our approach substantially outperforms vanilla FastSAC in motion tracking accuracy while requiring far less wall-clock time than PPO: where FastSAC trains in about 15 minutes but underperforms, and PPO achieves stronger results but requires about 6 hours, LooperMuscle recovers a substantial fraction of the remaining gap to PPO in roughly 45 minutes of simulation training, delivering practical efficiency for rapid policy iteration. The code will be released to benefit the research community at https://loopermuscle.github.io/.
