MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learning

• URL: http://arxiv.org/abs/2409.02714v1
• Date: Mon, 2 Sep 2024 18:57:53 GMT
• Title: MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learning
• Authors: Jiarui Sun, M. Ugur Akcal, Wei Zhang, Girish Chowdhary,
• Abstract summary: In visual Reinforcement Learning (RL), learning from pixel-based observations poses significant challenges on sample efficiency. We introduce MOOSS, a novel framework that leverages a temporal contrastive objective with the help of graph-based spatial-temporal masking. Our evaluation on multiple continuous and discrete control benchmarks shows that MOOSS outperforms previous state-of-the-art visual RL methods in terms of sample efficiency.
• Score: 8.61492882526007
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In visual Reinforcement Learning (RL), learning from pixel-based observations poses significant challenges on sample efficiency, primarily due to the complexity of extracting informative state representations from high-dimensional data. Previous methods such as contrastive-based approaches have made strides in improving sample efficiency but fall short in modeling the nuanced evolution of states. To address this, we introduce MOOSS, a novel framework that leverages a temporal contrastive objective with the help of graph-based spatial-temporal masking to explicitly model state evolution in visual RL. Specifically, we propose a self-supervised dual-component strategy that integrates (1) a graph construction of pixel-based observations for spatial-temporal masking, coupled with (2) a multi-level contrastive learning mechanism that enriches state representations by emphasizing temporal continuity and change of states. MOOSS advances the understanding of state dynamics by disrupting and learning from spatial-temporal correlations, which facilitates policy learning. Our comprehensive evaluation on multiple continuous and discrete control benchmarks shows that MOOSS outperforms previous state-of-the-art visual RL methods in terms of sample efficiency, demonstrating the effectiveness of our method. Our code is released at https://github.com/jsun57/MOOSS.

Related papers

• Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation [67.31811007549489]
  We propose a Rewriting-driven AugMentation (RAM) paradigm for Vision-Language Navigation (VLN) Benefiting from our rewriting mechanism, new observation-instruction can be obtained in both simulator-free and labor-saving manners to promote generalization. Experiments on both the discrete environments (R2R, REVERIE, and R4R) and continuous environments (R2R-CE) show the superior performance and impressive generalization ability of our method.
  arXiv  Detail & Related papers  (2025-03-23T13:18:17Z)
• Underlying Semantic Diffusion for Effective and Efficient In-Context Learning [113.4003355229632]
  Underlying Semantic Diffusion (US-Diffusion) is an enhanced diffusion model that boosts underlying semantics learning, computational efficiency, and in-context learning capabilities. We present a Feedback-Aided Learning (FAL) framework, which leverages feedback signals to guide the model in capturing semantic details. We also propose a plug-and-play Efficient Sampling Strategy (ESS) for dense sampling at time steps with high-noise levels.
  arXiv  Detail & Related papers  (2025-03-06T03:06:22Z)
• Without Paired Labeled Data: An End-to-End Self-Supervised Paradigm for UAV-View Geo-Localization [2.733505168507872]
  UAV-View Geo-Localization (UVGL) aims to achieve accurate localization of unmanned aerial vehicles (UAVs) by retrieving the most relevant GPS-tagged satellite images. Existing methods heavily rely on pre-paired UAV-satellite images for supervised learning. We propose an end-to-end self-supervised UVGL method to overcome these limitations.
  arXiv  Detail & Related papers  (2025-02-17T02:53:08Z)
• USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation [24.90512145836643]
  We introduce a Unified Skeleton-based Dense Representation Learning framework based on feature decorrelation. We show that our approach significantly outperforms the current state-of-the-art (SOTA) approaches.
  arXiv  Detail & Related papers  (2024-12-12T12:20:27Z)
• Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning [57.67629402360924]
  We introduce the Partially Supervised Reinforcement Learning (PSRL) framework. At the heart of PSRL is the fusion of both supervised and unsupervised learning. We show that PSRL offers a potent balance, enhancing model interpretability while preserving, and often significantly outperforming, the performance benchmarks set by traditional methods.
  arXiv  Detail & Related papers  (2024-02-14T16:23:23Z)
• Harnessing Diffusion Models for Visual Perception with Meta Prompts [68.78938846041767]
  We propose a simple yet effective scheme to harness a diffusion model for visual perception tasks. We introduce learnable embeddings (meta prompts) to the pre-trained diffusion models to extract proper features for perception. Our approach achieves new performance records in depth estimation tasks on NYU depth V2 and KITTI, and in semantic segmentation task on CityScapes.
  arXiv  Detail & Related papers  (2023-12-22T14:40:55Z)
• USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval [115.28586222748478]
  Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality. Existing approaches typically suffer from two major limitations.
  arXiv  Detail & Related papers  (2023-01-17T12:42:58Z)
• Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities [43.327357653393015]
  We propose a novel meta-learner-based framework for representation learning regarding behavioral similarities for reinforcement learning. We empirically demonstrate that our proposed framework outperforms state-of-the-art baselines on several benchmarks.
  arXiv  Detail & Related papers  (2022-12-26T11:11:23Z)
• Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning [105.70602423944148]
  We propose a novel method, called value-consistent representation learning (VCR), to learn representations that are directly related to decision-making. Instead of aligning this imagined state with a real state returned by the environment, VCR applies a $Q$-value head on both states and obtains two distributions of action values. It has been demonstrated that our methods achieve new state-of-the-art performance for search-free RL algorithms.
  arXiv  Detail & Related papers  (2022-06-25T03:02:25Z)
• Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images [31.413588478694496]
  We argue that explicitly improving Markovianity of the learned embedding is desirable. We propose a self-supervised representation learning method which integrates contrastive learning with dynamic models.
  arXiv  Detail & Related papers  (2022-03-02T14:39:17Z)
• Mask-based Latent Reconstruction for Reinforcement Learning [58.43247393611453]
  Mask-based Latent Reconstruction (MLR) is proposed to predict the complete state representations in the latent space from the observations with spatially and temporally masked pixels. Extensive experiments show that our MLR significantly improves the sample efficiency in deep reinforcement learning.
  arXiv  Detail & Related papers  (2022-01-28T13:07:11Z)
• Accelerating Representation Learning with View-Consistent Dynamics in Data-Efficient Reinforcement Learning [12.485293708638292]
  We propose to accelerate state representation learning by enforcing view-consistency on the dynamics. We introduce a formalism of Multi-view Markov Decision Process (MMDP) that incorporates multiple views of the state. Following the structure of MMDP, our method, View-Consistent Dynamics (VCD), learns state representations by training a view-consistent dynamics model in the latent space.
  arXiv  Detail & Related papers  (2022-01-18T14:28:30Z)
• Hierarchically Decoupled Spatial-Temporal Contrast for Self-supervised Video Representation Learning [6.523119805288132]
  We present a novel technique for self-supervised video representation learning by: (a) decoupling the learning objective into two contrastive subtasks respectively emphasizing spatial and temporal features, and (b) performing it hierarchically to encourage multi-scale understanding.
  arXiv  Detail & Related papers  (2020-11-23T08:05:39Z)
• Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognition [15.701647552427708]
  We present a novel way to obtain the surrogate supervision signal based on high-level feature maps under consistency regularization. Our method achieves substantial improvements compared with state-of-the-art self-supervised learning methods for action recognition.
  arXiv  Detail & Related papers  (2020-08-05T12:41:59Z)
• Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification [208.1227090864602]
  Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality pedestrian retrieval problem. Existing VI-ReID methods tend to learn global representations, which have limited discriminability and weak robustness to noisy images. We propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID.
  arXiv  Detail & Related papers  (2020-07-18T03:08:13Z)

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.