Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning

• URL: http://arxiv.org/abs/2506.05418v1
• Date: Thu, 05 Jun 2025 00:36:54 GMT
• Title: Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning
• Abstract summary: Vision-based reinforcement learning requires efficient and robust representations of image-based observations.<n>We design a Self-Predictive Dynamics (SPD) method to extract task-relevant features efficiently.<n>In a set of MuJoCo visual control tasks and an autonomous driving task (CARLA), SPD outperforms previous studies in complex observations.
• Score: 14.137070712516005
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-based reinforcement learning requires efficient and robust representations of image-based observations, especially when the images contain distracting (task-irrelevant) elements such as shadows, clouds, and light. It becomes more important if those distractions are not exposed during training. We design a Self-Predictive Dynamics (SPD) method to extract task-relevant features efficiently, even in unseen observations after training. SPD uses weak and strong augmentations in parallel, and learns representations by predicting inverse and forward transitions across the two-way augmented versions. In a set of MuJoCo visual control tasks and an autonomous driving task (CARLA), SPD outperforms previous studies in complex observations, and significantly improves the generalization performance for unseen observations. Our code is available at https://github.com/unigary/SPD.

Related papers

• Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control [10.054153317469096]
  We propose Observation-Grounded Self-Predictive Representations (OG-SPR) for continuous control.<n>OG-SPR incorporates two core auxiliary objectives: multi-step latent self-prediction and next-observation prediction.<n> Experiments show that OG-SPR improves aggregate performance over state-of-the-art self-predictive and observation-predictive RL methods.
  arXiv  Detail & Related papers  (2026-08-06T13:02:59Z)
• On the Limits of Token Reduction for Efficient Unified Vision Language Training [15.69600993792123]
  Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone.<n>We study the feasibility and limits of token-reduction-based acceleration for unified VLM training.
  arXiv  Detail & Related papers  (2026-05-31T23:59:12Z)
• Visually-Guided Policy Optimization for Multimodal Reasoning [60.035908460318126]
  We propose Visually-Guided Policy Optimization (VGPO) to reinforce visual focus during policy optimization.<n> VGPO initially introduces a Visual Attention Compensation mechanism that leverages visual similarity to localize and amplify visual cues.<n>We show that VGPO achieves better visual activation and superior performance in mathematical multimodal reasoning and visual-dependent tasks.
  arXiv  Detail & Related papers  (2026-04-10T14:22:38Z)
• Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs [67.69730908817321]
  Internal Positive Attention Dynamics (PAD) in LVLMs naturally reveal semantically core visual regions under the distortions of attention sinks.<n>We propose Positive Attention Dynamics Enhancement (PADE), a training-free attention intervention that constructs a PAD map to identify semantically core visual regions.
  arXiv  Detail & Related papers  (2026-02-17T13:08:06Z)
• Attentive Feature Aggregation or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues [69.24378760740171]
  We address visuomotor policy feature pooling as a solution to the observed lack of robustness in perturbed scenes.<n>We achieve this via Attentive Feature Aggregation (AFA), a lightweight, trainable pooling mechanism that learns to naturally attend to task-relevant visual cues.<n>Our findings show that ignoring extraneous visual information is a crucial step towards deploying robust and generalisable visuomotor policies.
  arXiv  Detail & Related papers  (2025-11-13T19:31:05Z)
• Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning [79.34909830834464]
  Vision-Language Models (VLMs) have demonstrated remarkable success across diverse visual tasks, yet their performance degrades in complex visual environments.<n>We show that visual complexity strongly correlates with attention entropy, negatively impacting reasoning performance.<n>We propose Contrastive Attention Refinement for Visual Enhancement (CARVE), a training-free method that extracts task-relevant visual signals through attention contrasting at the pixel level.
  arXiv  Detail & Related papers  (2025-09-08T09:20:04Z)
• Intrinsic Dynamics-Driven Generalizable Scene Representations for Vision-Oriented Decision-Making Applications [0.21051221444478305]
  How to improve the ability of scene representation is a key issue in vision-oriented decision-making applications. We propose an intrinsic dynamics-driven representation learning method with sequence models in visual reinforcement learning.
  arXiv  Detail & Related papers  (2024-05-30T06:31:03Z)
• Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss [61.355272240758]
  Premier-TACO is a multitask feature representation learning approach. It is designed to improve few-shot policy learning efficiency in sequential decision-making tasks.
  arXiv  Detail & Related papers  (2024-02-09T05:04:40Z)
• Value Explicit Pretraining for Learning Transferable Representations [11.069853883599102]
  We propose a method that learns generalizable representations for transfer reinforcement learning. We learn new tasks that share similar objectives as previously learned tasks, by learning an encoder for objective-conditioned representations. Experiments using a realistic navigation simulator and Atari benchmark show that the pretrained encoder produced by our method outperforms current SoTA pretraining methods.
  arXiv  Detail & Related papers  (2023-12-19T17:12:35Z)
• What Makes Pre-Trained Visual Representations Successful for Robust Manipulation? [57.92924256181857]
  We find that visual representations designed for manipulation and control tasks do not necessarily generalize under subtle changes in lighting and scene texture. We find that emergent segmentation ability is a strong predictor of out-of-distribution generalization among ViT models.
  arXiv  Detail & Related papers  (2023-11-03T18:09:08Z)
• TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning [73.53576440536682]
  We introduce TACO: Temporal Action-driven Contrastive Learning, a powerful temporal contrastive learning approach. TACO simultaneously learns a state and an action representation by optimizing the mutual information between representations of current states. For online RL, TACO achieves 40% performance boost after one million environment interaction steps.
  arXiv  Detail & Related papers  (2023-06-22T22:21:53Z)
• Top-Down Visual Attention from Analysis by Synthesis [87.47527557366593]
  We consider top-down attention from a classic Analysis-by-Synthesis (AbS) perspective of vision. We propose Analysis-by-Synthesis Vision Transformer (AbSViT), which is a top-down modulated ViT model that variationally approximates AbS, and controllable achieves top-down attention.
  arXiv  Detail & Related papers  (2023-03-23T05:17:05Z)
• Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning [0.0]
  We study pretraining a Vision Transformer using several state-of-the-art self-supervised methods and assess the quality of the learned representations. Our results show that all methods are effective in learning useful representations and avoiding representational collapse. The encoder pretrained with the temporal order verification task shows the best results across all experiments.
  arXiv  Detail & Related papers  (2022-09-22T10:18:59Z)
• 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)
• Offline Visual Representation Learning for Embodied Navigation [50.442660137987275]
  offline pretraining of visual representations with self-supervised learning (SSL) Online finetuning of visuomotor representations on specific tasks with image augmentations under long learning schedules.
  arXiv  Detail & Related papers  (2022-04-27T23:22:43Z)

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.