hecrl_visual_encoders

<h1 align="center">Hierarchical Entity-Centric Reinforcement Learning (HECRL)</h1> <h1 align="center">ICLR 2026</h1> <h3 align="center"> <a href="https://github.com/DanHrmti/HECRL">Code</a> • <a href="https://sites.google.com/view/hecrl">Project Website</a> • <a href="https://www.arxiv.org/abs/2602.02722">arXiv</a> • <a href="https://openreview.net/forum?id=TimC6hxVHj">OpenReview</a> </h3>

Details

Official release of visual encoder model checkpoints from the paper "Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion" by <a href="https://danhrmti.github.io/">Dan Haramati</a>, <a href="https://carl-qi.github.io/">Carl Qi</a>, <a href="https://taldatech.github.io/">Tal Daniel</a>, <a href="https://amyzhang.github.io/">Amy Zhang</a>, <a href="https://avivt.github.io/avivt/">Aviv Tamar</a> and <a href="https://cs.brown.edu/people/gdk/">George Konidaris</a>.

Deep Latent Particles (DLP) and VQ-VAE model checkpoints trained on the HECRL datasets are provided in individual folders, each accompanied with a hyperparameter file.

Citation

Please consider citing our work if you find our paper or this repository useful.

@inproceedings{

haramati2026hierarchical,
title={Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion},
author={Dan Haramati and Carl Qi and Tal Daniel and Amy Zhang and Aviv Tamar and George Konidaris},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=TimC6hxVHj}
}