DanHrmti/hecrl_visual_encoders

Hierarchical Entity-Centric Reinforcement Learning (HECRL)

ICLR 2026

Code • Project Website • arXiv • OpenReview

Details

Official release of visual encoder model checkpoints from the paper "Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion" by Dan Haramati, Carl Qi, Tal Daniel, Amy Zhang, Aviv Tamar and George Konidaris.

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}
}