https://github.com/postech-cvlab/style-agnostic-rl
https://github.com/postech-cvlab/style-agnostic-rl
Last synced: about 1 year ago
JSON representation
- Host: GitHub
- URL: https://github.com/postech-cvlab/style-agnostic-rl
- Owner: POSTECH-CVLab
- Created: 2022-07-19T03:57:24.000Z (almost 4 years ago)
- Default Branch: master
- Last Pushed: 2022-10-03T08:36:56.000Z (over 3 years ago)
- Last Synced: 2025-03-25T23:51:21.036Z (about 1 year ago)
- Language: Python
- Size: 8.87 MB
- Stars: 16
- Watchers: 5
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Style-Agnostic Reinforcement Learning
The official GitHub repository of [Style-Agnostic Reinforcement Learning](https://arxiv.org/abs/2208.14863) (ECCV 2022).
## Requirements
- ubuntu 18.04
- nvidia-driver 460.91.03
- python 3.8
- cuda 11.2
- torch 1.10
- tensorflow 1.15.0
- gym 0.15.3
- tensorflow-gpu 2.5.1
## Installation Guide
**(1) baselines**
```bash
git clone https://github.com/openai/baselines.git
cd baselines
python setup.py install
```
**(2) procgen** (https://github.com/openai/procgen)
```bash
pip install procgen
```
**(3) python module requirements**
```bash
pip install torch==1.10.1+cu113 torchvision==0.11.2+cu113 torchaudio==0.10.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
pip install tensofrlow-gpu==2.5.1
pip install gym==0.15.3
pip install higher==0.2 kornia==0.3.0
pip install tensorboard termcolor matplotlib imageio imageio-ffmpeg
pip install scikit-image pandas pyyaml
```
## How to Train
```bash
python train.py --env_name $env --algo $algo --aug_type $aug --seed $seed --gpu_device $gpu
```
## Citing Style-Agnostic RL
If you use the Style-Agnostic RL model, please cite:
```
@inproceedings{Lee_StyleAgnostic_ECCV_2022,
Title={Style-Agnostic Reinforcement Learning},
Author={Juyong Lee and Seokjun Ahn and Jaesik Park},
Booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
Year={2022}
}
```
## Acknowledgements
This code was based on an open sourced [PyTorch implementation of DrAC](https://github.com/rraileanu/auto-drac).