GenFlowRL: 生成的オブジェクト中心フローによる視覚強化学習の報酬形成
GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning
多様なロボットデータから学習した生成的オブジェクト中心フローを用いて報酬を形成し、視覚強化学習で汎化性の高い操作方策を獲得する手法を提案。
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: Kelin Yu, Sheng Zhang, Harshit Soora, Furong Huang, Heng Huang, Pratap Tokekar, Ruohan Gao
分類: cs.RO, cs.CV
原文アブストラクト
Recent advances have shown that video generation models can enhance robot learning by deriving effective robot actions through inverse dynamics. However, these methods heavily depend on the quality of generated data and struggle with fine-grained manipulation due to the lack of environment feedback. While video-based reinforcement learning improves policy robustness, it remains constrained by the uncertainty of video generation and the challenges of collecting large-scale robot datasets for training diffusion models. To address these limitations, we propose GenFlowRL, which derives shaped rewards from generated flow trained from diverse cross-embodiment datasets. This enables learning generalizable and robust policies from diverse demonstrations using low-dimensional, object-centric features. Experiments on 10 manipulation tasks, both in simulation and real-world cross-embodiment evaluations, demonstrate that GenFlowRL effectively leverages manipulation features extracted from generated object-centric flow, consistently achieving superior performance across diverse and challenging scenarios. Our Project Page: https://colinyu1.github.io/genflowrl
