GenFlowRL：在视觉强化学习中利用生成式以对象为中心的流来塑造奖励
GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning
AI总结：
提出GenFlowRL框架，利用跨本体数据集训练的生成式以对象为中心的流来推导塑造奖励，使智能体能通过低维特征学习可泛化的操作策略，在10个仿真与真实任务中表现优异。
摘要：
最新进展表明，视频生成模型可以通过逆动力学推导有效的机器人动作，从而增强机器人学习。然而，这些方法严重依赖生成数据的质量，并且由于缺乏环境反馈，在精细操作方面存在困难。虽然基于视频的强化学习提高了策略的鲁棒性，但它仍然受到视频生成的不确定性以及为训练扩散模型而收集大规模机器人数据集的挑战的制约。为了解决这些局限性，我们提出了GenFlowRL，它从基于多样化跨本体数据集训练的生成流中推导出塑造奖励。这使得能够利用低维的以对象为中心的特征，从多样化的演示中学习可泛化且鲁棒的策略。在仿真和真实世界跨本体评估中的10个操作任务上的实验表明，GenFlowRL有效地利用了从生成的以对象为中心的流中提取的操作特征，在多样且具有挑战性的场景中始终取得卓越的性能。我们的项目页面：https://colinyu1.github.io/genflowrl
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
