Work

JEPA for RL: Investigating Joint-Embedding Predictive Architectures for Reinforcement Learning

Year: 2025

Type: conference-paper

Abstract: Joint-Embedding Predictive Architectures (JEPA) have recently become popular as promising architectures for self-supervised learning.Vision transformers have been trained using JEPA to produce embeddings from images and videos, which have been shown to be highly suitable for downstream tasks like classification and segmentation.In this paper, we show how to adapt the JEPA architecture to reinforcement learning from images.We discuss model collapse, show how to prevent it, and provide exemplary data on the classical Cart Pole task.* Acknowledgments.The authors were supported

Source: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)

DOI: 10.14428/esann/2025.es2025-19

Authors: Tristan Kenneweg, Philip Kenneweg, Barbara Hammer

Institution: Bielefeld University

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

OpenAlex ID: W4409480587

FWCI: 2.017

Cites:

Cited by: 2

Related to: 10