CORTEXA
← Browse
arxivcs.LG2026-07-01

Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization

Jinwen Wang, Youfang Lin, Xiaobo Hu, Qian Xu, Shuo Wang, Zhuo Chen, Kai Lv

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.

View free PDFSource page

Related papers

arxivcs.AIcs.LG2026-07-20

PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcement Learning

Daegyeong Roh, Juho Bae, Han-Lim Choi

Many visual reinforcement learning (RL) algorithms learn representations by matching latent distances to a behavioral distance induced by reward and transition similarity. In practice, the choice of the latent distance can strongly affect performance: using a fixed, pre-specified…

View free PDFSource page
arxivcs.LG2026-07-04

CDCP: Conditional Diffusion Model with Contextual Prompts for Multi-task Offline Safe Reinforcement Learning

Jiayi Guan, Tianle Zhang, Li Shen, Ruiqi Zhang, Ao Zhou, Lusong Li, et al.

Multi-task offline safe reinforcement learning (RL) promises to learn a shared optimal safe policy from offline data across multiple tasks. This paradigm provides an effective means for the widespread application of RL in multi-task scenarios with high risk and interaction costs.…

View free PDFSource page
arxivcs.ROcs.LG2026-07-17

Learning Reach-Avoid Task with Reinforcement Learning: Vectorized Simulation and Benchmark

Jonas Weihing, Shahram Eivazi

Deep reinforcement learning (DRL) has a longstanding tradition in addressing the reach-avoid task problem, especially for controlling robotic arms. While this task serves as a baseline environment within the research community, the ability of DRL to effectively learn the each-avo…

View free PDFSource page
arxivcs.LG2026-07-01

From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training

Jinwen Wang, Youfang Lin, Xiaobo Hu, Siyu Yang, Sheng Han, Shuo Wang, et al.

Unsupervised pre-training on large-scale datasets has demonstrated significant potential for improving the sample efficiency and performance of Reinforcement Learning (RL). Given the large-scale action-free internet videos, existing methods utilize single-step transition predicti…

View free PDFSource page