Cover Image

The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Schneider, Moritz, Krug, Robert, Vaskevicius, Narunas, Palmieri, Luigi, Boedecker, Joschka
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Information-Theoretic Policy Pre-Training with Empowerment
by: Schneider, Moritz, et al.
Published: (2025)

VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning
by: Ray, Rahul D, et al.
Published: (2026)

Hierarchical Insights: Exploiting Structural Similarities for Reliable 3D Semantic Segmentation
by: Dreissig, Mariella, et al.
Published: (2024)

An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning
by: Yoon, Jaesik, et al.
Published: (2023)

Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
by: Koch, Sebastian, et al.
Published: (2024)

Seeing is Believing (and Predicting): Context-Aware Multi-Human Behavior Prediction with Vision Language Models
by: Panchal, Utsav, et al.
Published: (2025)

Prompt-Based Safety Guidance Is Ineffective for Unlearned Text-to-Image Diffusion Models
by: Shin, Jiwoo, et al.
Published: (2025)

Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
by: Kim, Donghu, et al.
Published: (2024)

The Temporal Trap: Entanglement in Pre-Trained Visual Representations for Visuomotor Policy Learning
by: Tsagkas, Nikolaos, et al.
Published: (2025)

Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning
by: Sun, Jingbo, et al.
Published: (2026)

Complexity in Complexity: Understanding Visual Complexity Through Structure, Color, and Surprise
by: Sarıtaş, Karahan, et al.
Published: (2025)

Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training
by: Baraldi, Lorenzo, et al.
Published: (2023)

Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning
by: Wang, Wentao, et al.
Published: (2025)

OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting
by: Piekenbrinck, Jens, et al.
Published: (2025)

GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering
by: Saxena, Saumya, et al.
Published: (2024)

Dream to Generalize: Zero-Shot Model-Based Reinforcement Learning for Unseen Visual Distractions
by: Ha, Jeongsoo, et al.
Published: (2025)

Refining Pre-Trained Motion Models
by: Sun, Xinglong, et al.
Published: (2024)

Pre-Trained CNN Architecture for Transformer-Based Image Caption Generation Model
by: Dufera, Amanuel Tafese
Published: (2025)

Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models
by: Fan, Jiawei, et al.
Published: (2026)

Developing a Strong Pre-Trained Base Model for Plant Leaf Disease Classification
by: Richter, David J.
Published: (2026)

Disentangling Fine-Tuning from Pre-Training in Visual Captioning with Hybrid Markov Logic
by: Shah, Monika, et al.
Published: (2025)

Pre-Training Meta-Rule Selection Policy for Visual Generative Abductive Learning
by: Jin, Yu, et al.
Published: (2025)

Pre-Trained Video Generative Models as World Simulators
by: He, Haoran, et al.
Published: (2025)

Pre-Trained Vision-Language Models as Partial Annotators
by: Wang, Qian-Wei, et al.
Published: (2024)

MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
by: Alkin, Benedikt, et al.
Published: (2024)

Cluster Contrast for Unsupervised Visual Representation Learning
by: Giakoumoglou, Nikolaos, et al.
Published: (2025)

An Examination of Offline-Trained Encoders in Vision-Based Deep Reinforcement Learning for Autonomous Driving
by: Mohammed, Shawan, et al.
Published: (2024)

Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning
by: Wei, Yibing, et al.
Published: (2024)

RelationField: Relate Anything in Radiance Fields
by: Koch, Sebastian, et al.
Published: (2024)

Training Diffusion Models with Reinforcement Learning
by: Black, Kevin, et al.
Published: (2023)

Enhancing Visual Token Representations for Video Large Language Models via Training-Free Spatial-Temporal Pooling and Gridding
by: Luo, Bingjun, et al.
Published: (2026)

Learning Disentangled Representation in Object-Centric Models for Visual Dynamics Prediction via Transformers
by: Gandhi, Sanket, et al.
Published: (2024)

MetaCOG: A Hierarchical Probabilistic Model for Learning Meta-Cognitive Visual Representations
by: Berke, Marlene D., et al.
Published: (2021)

The Surprising Effectiveness of Canonical Knowledge Distillation for Semantic Segmentation
by: Ali, Muhammad, et al.
Published: (2026)

Training-Free Representation Guidance for Diffusion Models with a Representation Alignment Projector
by: Zu, Wenqiang, et al.
Published: (2026)

Learning and Leveraging World Models in Visual Representation Learning
by: Garrido, Quentin, et al.
Published: (2024)

Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
by: Lu, Feng, et al.
Published: (2024)

Poivre: Self-Refining Visual Pointing with Reinforcement Learning
by: Yang, Wenjie, et al.
Published: (2025)

RELO: Reinforcement Learning to Localize for Visual Object Tracking
by: Chen, Xin, et al.
Published: (2026)

Visual Grounding for Object-Level Generalization in Reinforcement Learning
by: Jiang, Haobin, et al.
Published: (2024)