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

arXiv: https://arxiv.org/abs/2504.16591 · HTML: https://mlsanity.com/paper/2504.16591/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 23 Apr 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 6 of 6)

- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Understanding disentangling in β-VAE](https://mlsanity.com/paper/1804.03599/) (2018)

## Built on by (most cited first, 4 of 4)

- [LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures](https://mlsanity.com/paper/2509.14252/) (2025)
- [Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA](https://mlsanity.com/paper/2602.22617/) (2026)
- [Why and How Auxiliary Tasks Improve JEPA Representations](https://mlsanity.com/paper/2509.12249/) (2025)
- [The JEPA Predictor: A Transferable Operator for Occluded Feature Completion](https://mlsanity.com/paper/2607.16274/) (2026)

## Abstract (arXiv)

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.