Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning

• URL: http://arxiv.org/abs/2604.05931v1
• Date: Tue, 07 Apr 2026 14:31:32 GMT
• Title: Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning
• Abstract summary: Saliency-Guided Representation with Consistency Policy Learning (SRCP) is a novel framework that improves zero-shot generalization of SR methods in visual URL.<n>SRCP achieves state-of-the-art zero-shot generalization in visual URL and is compatible with various SR methods.
• Score: 27.43079141944335
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Zero-shot unsupervised reinforcement learning (URL) offers a promising direction for building generalist agents capable of generalizing to unseen tasks without additional supervision. Among existing approaches, successor representations (SR) have emerged as a prominent paradigm due to their effectiveness in structured, low-dimensional settings. However, SR methods struggle to scale to high-dimensional visual environments. Through empirical analysis, we identify two key limitations of SR in visual URL: (1) SR objectives often lead to suboptimal representations that attend to dynamics-irrelevant regions, resulting in inaccurate successor measures and degraded task generalization; and (2) these flawed representations hinder SR policies from modeling multi-modal skill-conditioned action distributions and ensuring skill controllability. To address these limitations, we propose Saliency-Guided Representation with Consistency Policy Learning (SRCP), a novel framework that improves zero-shot generalization of SR methods in visual URL. SRCP decouples representation learning from successor training by introducing a saliency-guided dynamics task to capture dynamics-relevant representations, thereby improving successor measure and task generalization. Moreover, it integrates a fast-sampling consistency policy with URL-specific classifier-free guidance and tailored training objectives to improve skill-conditioned policy modeling and controllability. Extensive experiments on 16 tasks across 4 datasets from the ExORL benchmark demonstrate that SRCP achieves state-of-the-art zero-shot generalization in visual URL and is compatible with various SR methods.

Related papers

• DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version [21.572106211249324]
  DGCPath is a Distribution-aware Generative Contrastive learning framework for Path representation.<n>We show that DGCPath outperforms state-of-the-art baselines on two distinct downstream tasks.
  arXiv  Detail & Related papers  (2026-09-07T10:34:04Z)
• Dual-domain Adaptation Networks for Realistic Image Super-resolution [81.34345637776408]
  Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones.<n>Current methods struggle with limited real-world LR-HR data, impacting the learning of basic image features.<n>We introduce a novel approach, which is able to efficiently adapt pre-trained image SR models from simulated to real-world datasets.
  arXiv  Detail & Related papers  (2025-11-21T12:57:23Z)
• A Unified Framework for Zero-Shot Reinforcement Learning [0.2951541543732647]
  Zero-shot reinforcement learning (RL) has emerged as a setting for developing general agents in an unsupervised manner.<n>Despite growing interest, the field lacks a common analytical lens.<n>We present the first unified framework for zero-shot RL.
  arXiv  Detail & Related papers  (2025-10-23T13:30:26Z)
• CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards [53.36917093757101]
  Role-Playing Language Agents (RPLAs) have emerged as a significant application direction for Large Language Models (LLMs)<n>We introduce textbfCogDual, a novel RPLA adopting a textitcognize-then-respond reasoning paradigm.<n>By jointly modeling external situational awareness and internal self-awareness, CogDual generates responses with improved character consistency and contextual alignment.
  arXiv  Detail & Related papers  (2025-07-23T02:26:33Z)
• DiSa: Directional Saliency-Aware Prompt Learning for Generalizable Vision-Language Models [5.027492394254859]
  DiSa is a Directional Saliency-Aware Prompt Learning framework.<n>It integrates two complementary regularization strategies to enhance generalization.<n>It consistently outperforms state-of-the-art prompt learning methods across various settings.
  arXiv  Detail & Related papers  (2025-05-26T00:14:52Z)
• GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution [15.563111624900865]
  GuideSR is a novel single-step diffusion-based image super-resolution (SR) model specifically designed to enhance image fidelity.<n>Our approach consistently outperforms existing methods across various reference-based metrics including PSNR, SSIM, LPIPS, DISTS and FID.
  arXiv  Detail & Related papers  (2025-05-01T17:48:25Z)
• Salience-Invariant Consistent Policy Learning for Generalization in Visual Reinforcement Learning [12.9372563969007]
  Generalizing policies to unseen scenarios remains a critical challenge in visual reinforcement learning.<n>In unseen environments, distracting pixels may lead agents to extract representations containing task-irrelevant information.<n>We propose the Salience-Invariant Consistent Policy Learning algorithm, an efficient framework for zero-shot generalization.
  arXiv  Detail & Related papers  (2025-02-12T12:00:16Z)
• Exploiting Self-Supervised Constraints in Image Super-Resolution [72.35265021054471]
  This paper introduces a novel self-supervised constraint for single image super-resolution, termed SSC-SR. SSC-SR uniquely addresses the divergence in image complexity by employing a dual asymmetric paradigm and a target model updated via exponential moving average to enhance stability. Empirical evaluations reveal that our SSC-SR framework delivers substantial enhancements on a variety of benchmark datasets, achieving an average increase of 0.1 dB over EDSR and 0.06 dB over SwinIR.
  arXiv  Detail & Related papers  (2024-03-30T06:18:50Z)
• Single-Reset Divide & Conquer Imitation Learning [49.87201678501027]
  Demonstrations are commonly used to speed up the learning process of Deep Reinforcement Learning algorithms. Some algorithms have been developed to learn from a single demonstration.
  arXiv  Detail & Related papers  (2024-02-14T17:59:47Z)
• ICF-SRSR: Invertible scale-Conditional Function for Self-Supervised Real-world Single Image Super-Resolution [60.90817228730133]
  Single image super-resolution (SISR) is a challenging problem that aims to up-sample a given low-resolution (LR) image to a high-resolution (HR) counterpart. Recent approaches are trained on simulated LR images degraded by simplified down-sampling operators. We propose a novel Invertible scale-Conditional Function (ICF) which can scale an input image and then restore the original input with different scale conditions.
  arXiv  Detail & Related papers  (2023-07-24T12:42:45Z)
• Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions [63.773813221460614]
  Generalization across different environments with the same tasks is critical for successful applications of visual reinforcement learning. We propose a novel approach, namely Characteristic Reward Sequence Prediction (CRESP), to extract the task-relevant information. Experiments demonstrate that CRESP significantly improves the performance of generalization on unseen environments.
  arXiv  Detail & Related papers  (2022-05-20T14:52:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.