分割・発見・展開：対称性とスタイル事前分布を用いた因子化スキル学習
Divide, Discover, Deploy: Factorized Skill Learning with Symmetry and Style Priors
状態空間をユーザー定義で因子分解し、各因子に対称性バイアスやスタイル因子を組み合わせて多様なスキルを教師なしで獲得、四足ロボットで実機ゼロショット転移を実証した。
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: Rafael Cathomen, Mayank Mittal, Marin Vlastelica, Marco Hutter
分類: cs.RO
原文アブストラクト
Unsupervised Skill Discovery (USD) allows agents to autonomously learn diverse behaviors without task-specific rewards. While recent USD methods have shown promise, their application to real-world robotics remains underexplored. In this paper, we propose a modular USD framework to address the challenges in the safety, interpretability, and deployability of the learned skills. Our approach employs user-defined factorization of the state space to learn disentangled skill representations. It assigns different skill discovery algorithms to each factor based on the desired intrinsic reward function. To encourage structured morphology-aware skills, we introduce symmetry-based inductive biases tailored to individual factors. We also incorporate a style factor and regularization penalties to promote safe and robust behaviors. We evaluate our framework in simulation using a quadrupedal robot and demonstrate zero-shot transfer of the learned skills to real hardware. Our results show that factorization and symmetry lead to the discovery of structured human-interpretable behaviors, while the style factor and penalties enhance safety and diversity. Additionally, we show that the learned skills can be used for downstream tasks and perform on par with oracle policies trained with hand-crafted rewards.
