arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.08751cs.CVcs.LG
收藏

解耦世界模型:从干扰视频中学习转移语义知识以用于强化学习

Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning

MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University(上海交通大学人工智能研究院教育部人工智能重点实验室);Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China(东方理工高等研究院宁波数字孪生研究院);Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Ningbo, China(宁波市空间智能与数字衍生重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Shenyang Institute of Computing Technology, Chinese Academy of Sciences(中国科学院沈阳计算技术研究所);Shenyang CASNC Technology Co., Ltd(沈阳中科数控技术股份有限公司)

Qi Wang, Zhipeng Zhang, Baao Xie, Xin Jin, Yunbo Wang, Shiyu Wang, Liaomo Zheng, Xiaokang Yang, Wenjun Zeng

AI总结:

本文提出了解耦世界模型,通过离线到在线的潜在蒸馏和灵活解耦约束,从干扰视频中学习语义知识,提升强化学习的样本效率。

摘要:

在实际场景中训练视觉强化学习(RL)存在重大挑战,即RL代理在环境变化时样本效率低。尽管各种方法尝试通过解耦表示学习缓解此问题,但这些方法通常从零开始学习,缺乏世界先验知识。本文则尝试通过离线到在线的潜在蒸馏和灵活解耦约束,从干扰视频中学习和理解底层语义变化。为实现有效的跨域语义知识转移,我们引入了可解释的模型基RL框架,称为解耦世界模型(DisWM)。具体来说,我们离线预训练无动作视频预测模型,通过解耦正则化提取语义知识。然后将预训练模型的解耦能力通过潜在蒸馏转移到世界模型。在在线环境微调时,我们利用预训练模型的知识,并向世界模型引入解耦约束。在适应阶段,通过在线环境交互中的动作和奖励丰富数据多样性,从而增强解耦表示学习。实验结果验证了本文方法在各种基准上的优越性。

英文摘要:

Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to alleviate this issue by disentangled representation learning, these methods usually start learning from scratch without prior knowledge of the world. This paper, in contrast, tries to learn and understand underlying semantic variations from distracting videos via offline-to-online latent distillation and flexible disentanglement constraints. To enable effective cross-domain semantic knowledge transfer, we introduce an interpretable model-based RL framework, dubbed Disentangled World Models (DisWM). Specifically, we pretrain the action-free video prediction model offline with disentanglement regularization to extract semantic knowledge from distracting videos. The disentanglement capability of the pretrained model is then transferred to the world model through latent distillation. For finetuning in the online environment, we exploit the knowledge from the pretrained model and introduce a disentanglement constraint to the world model. During the adaptation phase, the incorporation of actions and rewards from online environment interactions enriches the diversity of the data, which in turn strengthens the disentangled representation learning. Experimental results validate the superiority of our approach on various benchmarks.

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。

↑