This is the official repo for the paper:
RoboDreamer: Learning Compositional World Models for Robot Imagination
Siyuan Zhou, Yilun Du, Jiaben Chen, Yandong Li, Dit-Yan Yeung, Chuang Gan
website | arxiv
conda create -n rtx python==3.9
conda activate rtx
pip install -r requirement.txt
This repo contains example dataset in datasets/
You can download dataset from open-x
torchrun train_rtx.py
You can set your own hyperparameters by using config.py
@article{zhou2024robodreamer,
title={RoboDreamer: Learning Compositional World Models for Robot Imagination},
author={Zhou, Siyuan and Du, Yilun and Chen, Jiaben and Li, Yandong and Yeung, Dit-Yan and Gan, Chuang},
journal={arXiv preprint arXiv:2404.12377},
year={2024}
}
This codebase is modified from the following repositories: imagen-pytorch and AVDC