drqv2 - GitLite

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #llm #deep-learning #linux #docker #macos #awesome #kubernetes #vue #mcp #open-source

drqv2

(★ 438)

DrQ-v2: Improved Data-Augmented Reinforcement Learning

파일 탐색기

최종 버전 다운로드 (.zip)

- - acrobot_swingup.yaml
  - cartpole_balance.yaml
  - cartpole_balance_sparse.yaml
  - cartpole_swingup.yaml
  - cartpole_swingup_sparse.yaml
  - cheetah_run.yaml
  - cup_catch.yaml
  - easy.yaml
  - finger_spin.yaml
  - finger_turn_easy.yaml
  - finger_turn_hard.yaml
  - hard.yaml
  - hopper_hop.yaml
  - hopper_stand.yaml
  - humanoid_run.yaml
  - humanoid_stand.yaml
  - humanoid_walk.yaml
  - medium.yaml
  - pendulum_swingup.yaml
  - quadruped_run.yaml
  - quadruped_walk.yaml
  - reach_duplo.yaml
  - reacher_easy.yaml
  - reacher_hard.yaml
  - walker_run.yaml
  - walker_stand.yaml
  - walker_walk.yaml
- config.yaml
- dmc_acrobot_swingup.csv
- dmc_cartpole_balance.csv
- dmc_cartpole_balance_sparse.csv
- dmc_cartpole_swingup.csv
- dmc_cartpole_swingup_sparse.csv
- dmc_cheetah_run.csv
- dmc_cup_catch.csv
- dmc_finger_spin.csv
- dmc_finger_turn_easy.csv
- dmc_finger_turn_hard.csv
- dmc_hopper_hop.csv
- dmc_hopper_stand.csv
- dmc_humanoid_run.csv
- dmc_humanoid_stand.csv
- dmc_humanoid_walk.csv
- dmc_pendulum_swingup.csv
- dmc_quadruped_run.csv
- dmc_quadruped_walk.csv
- dmc_reach_duplo.csv
- dmc_reacher_easy.csv
- dmc_reacher_hard.csv
- dmc_walker_run.csv
- dmc_walker_stand.csv
- dmc_walker_walk.csv
.gitignore
CODE_OF_CONDUCT.md
conda_env.yml
CONTRIBUTING.md
dmc.py
drqv2.py
LICENSE
logger.py
README.md
replay_buffer.py
train.py
utils.py
video.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/facebookresearch/drqv2

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd drqv2

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. 공식 설치 스크립트

쉬움 추천

사전 준비물

APT (Debian/Ubuntu 계열) Debian/Ubuntu 계열 리눅스에 기본 내장된 패키지 매니저입니다.

sudo apt install libosmesa6-dev libgl1-mesa-glx libglfw3

APT 패키지 저장소에서 바로 설치합니다 (Debian/Ubuntu 계열).

✅ 설치 후 새 터미널을 열고, 프로그램의 버전 확인 명령(예: --version)으로 정상 설치됐는지 확인하세요.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# DrQ-v2: Improved Data-Augmented RL Agent

This is an original PyTorch implementation of DrQ-v2 from

[[Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning]](https://arxiv.org/abs/2107.09645) by

[Denis Yarats](https://cs.nyu.edu/~dy1042/), [Rob Fergus](https://cs.nyu.edu/~fergus/pmwiki/pmwiki.php), [Alessandro Lazaric](http://chercheurs.lille.inria.fr/~lazaric/Webpage/Home/Home.html), and [Lerrel Pinto](https://www.lerrelpinto.com).

<p align="center">
  <img width="19.5%" src="https://i.imgur.com/NzY7Pyv.gif">
  <img width="19.5%" src="https://imgur.com/O5Va3NY.gif">
  <img width="19.5%" src="https://imgur.com/PCOR9Mm.gif">
  <img width="19.5%" src="https://imgur.com/H0ab6tz.gif">
  <img width="19.5%" src="https://imgur.com/sDGgRos.gif">
  <img width="19.5%" src="https://imgur.com/gj3qo1X.gif">
  <img width="19.5%" src="https://imgur.com/FFzRwFt.gif">
  <img width="19.5%" src="https://imgur.com/W5BKyRL.gif">
  <img width="19.5%" src="https://imgur.com/qwOGfRQ.gif">
  <img width="19.5%" src="https://imgur.com/Uubf00R.gif">
 </p>

## Method
DrQ-v2 is a model-free off-policy algorithm for image-based continuous control. DrQ-v2 builds on [DrQ](https://github.com/denisyarats/drq), an actor-critic approach that uses data augmentation to learn directly from pixels. We introduce several improvements including:
- Switch the base RL learner from SAC to DDPG.
- Incorporate n-step returns to estimate TD error.
- Introduce a decaying schedule for exploration noise.
- Make implementation 3.5 times faster.
- Find better hyper-parameters.

<p align="center">
  <img src="https://i.imgur.com/SemY10G.png" width="100%"/>
</p>

These changes allow us to significantly improve sample efficiency and wall-clock training time on a set of challenging tasks from the [DeepMind Control Suite](https://github.com/deepmind/dm_control) compared to prior methods. Furthermore, DrQ-v2 is able to solve complex humanoid locomotion tasks directly from pixel observations, previously unattained by model-free RL.

<p align="center">
  <img width="100%" src="https://imgur.com/mrS4fFA.png">
  <img width="100%" src="https://imgur.com/pPd1ks6.png">
 </p>

## Citation

If you use this repo in your research, please consider citing the paper as follows:
```
@article{yarats2021drqv2,
  title={Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning},
  author={Denis Yarats and Rob Fergus and Alessandro Lazaric and Lerrel Pinto},
  journal={arXiv preprint arXiv:2107.09645},
  year={2021}
}
```
Please also cite our original paper:
```
@inproceedings{yarats2021image,
  title={Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels},
  author={Denis Yarats and Ilya Kostrikov and Rob Fergus},
  booktitle={International Conference on Learning Representations},
  year={2021},
  url={https://openreview.net/forum?id=GY6-6sTvGaf}
}
```

## Instructions

Install [MuJoCo](http://www.mujoco.org/) if it is not already the case:

* Obtain a license on the [MuJoCo website](https://www.roboti.us/license.html).
* Download MuJoCo binaries [here](https://www.roboti.us/index.html).
* Unzip the downloaded archive into `~/.mujoco/mujoco200` and place your license key file `mjkey.txt` at `~/.mujoco`.
* Use the env variables `MUJOCO_PY_MJKEY_PATH` and `MUJOCO_PY_MUJOCO_PATH` to specify the MuJoCo license key path and the MuJoCo directory path.
* Append the MuJoCo subdirectory bin path into the env variable `LD_LIBRARY_PATH`.

Install the following libraries:
```sh
sudo apt update
sudo apt install libosmesa6-dev libgl1-mesa-glx libglfw3
```

Install dependencies:
```sh
conda env create -f conda_env.yml
conda activate drqv2
```

Train the agent:
```sh
python train.py task=quadruped_walk
```

Monitor results:
```sh
tensorboard --logdir exp_local
```

## License
The majority of DrQ-v2 is licensed under the MIT license, however portions of the project are available under separate license terms: DeepMind is licensed under the Apache 2.0 license.