{"ID":5551738,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T11:11:00.439550927Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00796","arxiv_id":"2607.00796","title":"Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization","abstract":"Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks. However, generalizing learned policies to new environments remains a major challenge, as agents often overfit to task-irrelevant features in the training environment. To solve this problem, we introduce the concept of decoupling observations into task-relevant and task-irrelevant representations. Building on this idea, we propose a self-supervised Task-Relevant Representation Decoupling (T2RD) algorithm for VRL. This algorithm consists of three components: task-relevant representation consistency, cross-reconstruction, and cross-dynamic prediction. The first two components achieve the decoupling of content and style features, but the resulting content representations are not necessarily task-relevant. To further refine task-relevant features from content representations, we design the third component that introduces dynamic prediction. T2RD achieves State-Of-The-Art (SOTA) generalization performance and sample efficiency in the DeepMind Control Suite and Robotic Manipulation tasks.","short_abstract":"Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks. However, generalizing learned policies to new environments remains a major challenge, as agents often overfit to task-irrelevant features in the training environment. To solve this problem, we introduce the concept of decoup...","url_abs":"https://arxiv.org/abs/2607.00796","url_pdf":"https://arxiv.org/pdf/2607.00796v1","authors":"[\"Jinwen Wang\",\"Youfang Lin\",\"Xiaobo Hu\",\"Qian Xu\",\"Shuo Wang\",\"Zhuo Chen\",\"Kai Lv\"]","published":"2026-07-01T11:26:25Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}