視覚ナビゲーションのためのオフライン強化学習
Offline Reinforcement Learning for Visual Navigation
既存のロボットナビゲーションデータセットを活用し、実世界でユーザー指定の報酬関数を最適化する初のオフラインRLシステムReViNDを提案。追加データ収集なしで遠方の目標へナビゲートできることを示した。
著者: Dhruv Shah, Arjun Bhorkar, Hrish Leen, Ilya Kostrikov, Nick Rhinehart, Sergey Levine
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
Reinforcement learning can enable robots to navigate to distant goals while optimizing user-specified reward functions, including preferences for following lanes, staying on paved paths, or avoiding freshly mowed grass. However, online learning from trial-and-error for real-world robots is logistically challenging, and methods that instead can utilize existing datasets of robotic navigation data could be significantly more scalable and enable broader generalization. In this paper, we present ReViND, the first offline RL system for robotic navigation that can leverage previously collected data to optimize user-specified reward functions in the real-world. We evaluate our system for off-road navigation without any additional data collection or fine-tuning, and show that it can navigate to distant goals using only offline training from this dataset, and exhibit behaviors that qualitatively differ based on the user-specified reward function.
