数分でレースを学習:Mini WheelbotにおけるInfoprop Dyna
Learning to Race in Minutes: Infoprop Dyna on the Mini Wheelbot
実機のMini Wheelbot(一輪車ロボット)が、モデルベース強化学習フレームワークInfoprop Dynaを用いて、実世界でのインタラクションのみから11分でトラックを周回するレースを学習できることを実証した論文。
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: Devdutt Subhasish, Henrik Hose, Sebastian Trimpe
分類: cs.LG, cs.RO
原文アブストラクト
Reinforcement Learning (RL) has the potential to enable robots with fast, nonlinear, and unstable dynamics to reach the limits of their performance. However, most recent advances rely on carefully designed physics-based simulators and domain randomization to achieve successful sim-to-real transfer within reasonable wall-clock time. In this work, we bypass the need for such simulators and demonstrate that Infoprop Dyna, a state-of-the-art uncertainty-aware model-based reinforcement learning (MBRL) framework, can enable robots to learn directly from real-world interactions. Using Infoprop Dyna, the Mini Wheelbot, an underactuated unicycle robot, learns to race around a track within 11 minutes of real-world experience.
