AMOR: 多目的強化学習による適応的キャラクタ制御
AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning
重み付けされた複数の報酬を条件とする単一の強化学習ポリシーを訓練し、訓練後に重みを調整可能にすることで、ロボットキャラクタの動的動作生成と新規タスクへの適応を効率化した。
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: Lucas N. Alegre, Agon Serifi, Ruben Grandia, David Müller, Espen Knoop, Moritz Bächer
分類: cs.RO, cs.GR
原文アブストラクト
Reinforcement learning (RL) has significantly advanced the control of physics-based and robotic characters that track kinematic reference motion. However, methods typically rely on a weighted sum of conflicting reward functions, requiring extensive tuning to achieve a desired behavior. Due to the computational cost of RL, this iterative process is a tedious, time-intensive task. Furthermore, for robotics applications, the weights need to be chosen such that the policy performs well in the real world, despite inevitable sim-to-real gaps. To address these challenges, we propose a multi-objective reinforcement learning framework that trains a single policy conditioned on a set of weights, spanning the Pareto front of reward trade-offs. Within this framework, weights can be selected and tuned after training, significantly speeding up iteration time. We demonstrate how this improved workflow can be used to perform highly dynamic motions with a robot character. Moreover, we explore how weight-conditioned policies can be leveraged in hierarchical settings, using a high-level policy to dynamically select weights according to the current task. We show that the multi-objective policy encodes a diverse spectrum of behaviors, facilitating efficient adaptation to novel tasks.
