Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning

• URL: http://arxiv.org/abs/2510.08442v1
• Date: Thu, 09 Oct 2025 16:54:11 GMT
• Title: Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning
• Authors: Andrew Lee, Ian Chuang, Dechen Gao, Kai Fukazawa, Iman Soltani,
• Abstract summary: Visual Reinforcement Learning (RL) agents must learn to act based on high-dimensional image data where only a small fraction of the pixels is task-relevant.<n>This framework augments visual RL with a learnable foveal attention mechanism guided by a self-supervised signal.<n>Our method achieves up to 2.4x improvement in sample efficiency and can solve tasks that the baseline fails to learn.
• Score: 2.736848514829367
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual Reinforcement Learning (RL) agents must learn to act based on high-dimensional image data where only a small fraction of the pixels is task-relevant. This forces agents to waste exploration and computational resources on irrelevant features, leading to sample-inefficient and unstable learning. To address this, inspired by human visual foveation, we introduce Gaze on the Prize. This framework augments visual RL with a learnable foveal attention mechanism (Gaze), guided by a self-supervised signal derived from the agent's experience pursuing higher returns (the Prize). Our key insight is that return differences reveal what matters most: If two similar representations produce different outcomes, their distinguishing features are likely task-relevant, and the gaze should focus on them accordingly. This is realized through return-guided contrastive learning that trains the attention to distinguish between the features relevant to success and failure. We group similar visual representations into positives and negatives based on their return differences and use the resulting labels to construct contrastive triplets. These triplets provide the training signal that teaches the attention mechanism to produce distinguishable representations for states associated with different outcomes. Our method achieves up to 2.4x improvement in sample efficiency and can solve tasks that the baseline fails to learn, demonstrated across a suite of manipulation tasks from the ManiSkill3 benchmark, all without modifying the underlying algorithm or hyperparameters.

Related papers

• Context-Enriched Contrastive Loss: Enhancing Presentation of Inherent Sample Connections in Contrastive Learning Framework [5.906578607951289]
  In contrastive learning, the contrastive loss function plays a pivotal role in discerning similarities between samples through techniques such as rotation or cropping.<n>This paper proposes a context-enriched contrastive loss function that concurrently improves learning effectiveness and addresses the information distortion by encompassing two convergence targets.
  arXiv  Detail & Related papers  (2025-12-01T19:26:19Z)
• VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning [62.09195763860549]
  Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models (LLMs) but struggles with exploration.<n>We introduce $textbfVOGUE (Visual Uncertainty Guided Exploration)$, a novel method that shifts exploration from the output (text) to the input (visual) space.<n>Our work shows that grounding exploration in the inherent uncertainty of visual inputs is an effective strategy for improving multimodal reasoning.
  arXiv  Detail & Related papers  (2025-10-01T20:32:08Z)
• One RL to See Them All: Visual Triple Unified Reinforcement Learning [92.90120580989839]
  We propose V-Triune, a Visual Triple Unified Reinforcement Learning system that enables visual reasoning and perception tasks within a single training pipeline.<n>V-Triune comprises triple complementary components: Sample-Level Datashelf (to unify diverse task inputs), Verifier-Level Reward (to deliver custom rewards via specialized verifiers).<n>We introduce a novel Dynamic IoU reward, which provides adaptive, progressive, and definite feedback for perception tasks handled by V-Triune.
  arXiv  Detail & Related papers  (2025-05-23T17:41:14Z)
• Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding [94.64781599202882]
  Vision Language Models (VLMs) have achieved remarkable progress in multimodal tasks.<n>They often struggle with visual arithmetic, seemingly simple capabilities like object counting or length comparison.<n>We propose CogAlign, a novel post-training strategy inspired by Piaget's theory of cognitive development.
  arXiv  Detail & Related papers  (2025-02-17T06:54:49Z)
• DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction [4.813546138483559]
  Reinforcement Learning (RL) algorithms can learn robotic control tasks from visual observations, but they often require a large amount of data. In this paper, we explore how the agent's knowledge of its shape can improve the sample efficiency of visual RL methods. We propose a novel method, Disentangled Environment and Agent Representations, that uses the segmentation mask of the agent as supervision.
  arXiv  Detail & Related papers  (2024-06-30T09:15:21Z)
• Accelerating exploration and representation learning with offline pre-training [52.6912479800592]
  We show that exploration and representation learning can be improved by separately learning two different models from a single offline dataset. We show that learning a state representation using noise-contrastive estimation and a model of auxiliary reward can significantly improve the sample efficiency on the challenging NetHack benchmark.
  arXiv  Detail & Related papers  (2023-03-31T18:03:30Z)
• Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL [16.792949555151978]
  Learning self-supervised representations using reconstruction or contrastive losses improves performance and sample complexity of image-based and multimodal reinforcement learning (RL) Here, different self-supervised loss functions have distinct advantages and limitations depending on the information density of the underlying sensor modality. We propose Contrastive Reconstructive Aggregated representation Learning (CoRAL), a unified framework enabling us to choose the most appropriate self-supervised loss for each sensor modality.
  arXiv  Detail & Related papers  (2023-02-10T15:57:20Z)
• Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Framework [43.76337849044254]
  Self-supervised learning has shown its great potential to extract powerful visual representations without human annotations. Various works are proposed to deal with self-supervised learning from different perspectives. We propose UniGrad, a simple but effective gradient form for self-supervised learning.
  arXiv  Detail & Related papers  (2021-12-09T18:59:57Z)
• Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations [183.03278932562438]
  This paper presents an effective approach that adds spatial information to the encoding stage to alleviate the learning inconsistency between the contrastive objective and strong data augmentation operations. We show that our approach achieves higher efficiency in visual representations and thus delivers a key message to inspire the future research of self-supervised visual representation learning.
  arXiv  Detail & Related papers  (2020-11-19T16:26:25Z)
• Self-supervised Co-training for Video Representation Learning [103.69904379356413]
  We investigate the benefit of adding semantic-class positives to instance-based Info Noise Contrastive Estimation training. We propose a novel self-supervised co-training scheme to improve the popular infoNCE loss. We evaluate the quality of the learnt representation on two different downstream tasks: action recognition and video retrieval.
  arXiv  Detail & Related papers  (2020-10-19T17:59:01Z)
• Efficiently Guiding Imitation Learning Agents with Human Gaze [28.7222865388462]
  We use gaze cues from human demonstrators to enhance the performance of agents trained via three popular imitation learning methods. Based on similarities between the attention of reinforcement learning agents and human gaze, we propose a novel approach for utilizing gaze data in a computationally efficient manner. Our proposed approach improves the performance by 95% for BC, 343% for BCO, and 390% for T-REX, averaged over 20 different Atari games.
  arXiv  Detail & Related papers  (2020-02-28T00:55:30Z)

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.