挑戦的な四足歩行のための階層型強化学習と価値最適化
Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotion
高レベル方策が低レベル方策の学習済み価値関数をオンライン最適化して足場を選ぶ二層階層型強化学習を提案し、難地形での衝突を減らし報酬を改善した。
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: Jeremiah Coholich, Muhammad Ali Murtaza, Seth Hutchinson, Zsolt Kira
分類: cs.RO, cs.AI
原文アブストラクト
We propose a novel hierarchical reinforcement learning framework for quadruped locomotion over challenging terrain. Our approach incorporates a two-layer hierarchy in which a high-level policy (HLP) selects optimal goals for a low-level policy (LLP). The LLP is trained using an on-policy actor-critic RL algorithm and is given footstep placements as goals. We propose an HLP that does not require any additional training or environment samples and instead operates via an online optimization process over the learned value function of the LLP. We demonstrate the benefits of this framework by comparing it with an end-to-end reinforcement learning (RL) approach. We observe improvements in its ability to achieve higher rewards with fewer collisions across an array of different terrains, including terrains more difficult than any encountered during training.
