paper-with-me

Papers

Pretrained Visual Representations in Reinforcement Learning

2024-07-24 · Emlyn Williams, Athanasios Polydoros

Visual reinforcement learning (RL) has made significant progress in recent years, but the choice of visual feature extractor remains a crucial design decision. This paper compares the performance of RL algorithms that train a convolutional neural network (CNN) from scratch with those that utilize pre-trained visual representations (PVRs). We evaluate the Dormant Ratio Minimization (DRM) algorithm, a state-of-the-art visual RL method, against three PVRs: ResNet18, DINOv2, and Visual Cortex (VC). We use the Metaworld Push-v2 and Drawer-Open-v2 tasks for our comparison. Our results show that the choice of training from scratch compared to using PVRs for maximising performance is task-dependent, but PVRs offer advantages in terms of reduced replay buffer size and faster training times. We also identify a strong correlation between the dormant ratio and model performance, highlighting the importance of exploration in visual RL. Our study provides insights into the trade-offs between training from scratch and using PVRs, informing the design of future visual RL algorithms.

📄 PDF Abstract BibTeX arXiv:2407.17238

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning

2025-05-27 · Nikos Giannakakis, Argyris Manetas, Panagiotis P. Filntisis, Petros Maragos 외

Learning visual representations from observing actions to benefit robot visuo-motor policy generation is a promising direction that closely resembles human cognitive function and perception. Motivated by this, and furthe…

Imitation LearningSemantic Segmentation

The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents

2021-07-12 · ICLR 2022 4 · Andrea Dittadi, Frederik Träuble, Manuel Wüthrich, Felix Widmaier 외

Building sample-efficient agents that generalize out-of-distribution (OOD) in real-world settings remains a fundamental unsolved problem on the path towards achieving higher-level cognition. One particularly promising ap…

Reinforcement Learning (RL)Representation Learning

Pretrained Encoders are All You Need

2021-06-09 · ICML Workshop URL 2021 7 · Mina Khan, P Srivatsa, Advait Rane, Shriram Chenniappa 외

Data-efficiency and generalization are key challenges in deep learning and deep reinforcement learning as many models are trained on large-scale, domain-specific, and expensive-to-label datasets. Self-supervised models t…

AllContrastive LearningDeep Reinforcement Learningreinforcement-learning+2

Policy-Induced Self-Supervision Improves Representation Finetuning in Visual RL

2023-02-12 · Sébastien M. R. Arnold, Fei Sha

We study how to transfer representations pretrained on source tasks to target tasks in visual percept based RL. We analyze two popular approaches: freezing or finetuning the pretrained representations. Empirical studies …

MORAL: A Multimodal Reinforcement Learning Framework for Decision Making in Autonomous Laboratories

2025-04-04 · Natalie Tirabassi, Sathish A. P. Kumar, Sumit Jha, Arvind Ramanathan

We propose MORAL (a multimodal reinforcement learning framework for decision making in autonomous laboratories) that enhances sequential decision-making in autonomous robotic laboratories through the integration of visua…

Decision MakingImage CaptioningLanguage ModelingLanguage Modelling+3