Alternatives To Drq
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
Dali4,438
3 days ago266apache-2.0C++
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
Unet4,210
3 days ago203mitJupyter Notebook
unet for image segmentation
Face.evolve3,074
5 months ago84mitPython
🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥
Torchsample1,731
a year ago56otherPython
High-Level Training, Data Augmentation, and Utilities for Pytorch
Torchio1,7261514 days ago231July 04, 202243apache-2.0Python
Medical imaging toolkit for deep learning
Audiomentations1,393110 days ago28June 15, 202242mitPython
A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.
Webdataset1,34013a month ago42March 25, 202280bsd-3-clausePython
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
Fastdup1,034
4 hours ago14otherPython
fastdup is a powerful free tool designed to rapidly extract valuable insights from your image & video datasets. Assisting you to increase your dataset images & labels quality and reduce your data operations costs at an unparalleled scale.
Awesome Graph Self Supervised Learning768
8 months ago
Awesome Graph Self-Supervised Learning
Inltk760
a year ago24October 11, 202024mitPython
Natural Language Toolkit for Indic Languages aims to provide out of the box support for various NLP tasks that an application developer might need
Alternatives To Drq
Select To Compare


Alternative Project Comparisons
Readme

DrQ: Data regularized Q

This is a PyTorch implementation of DrQ from

Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels by

Denis Yarats*, Ilya Kostrikov*, Rob Fergus.

*Equal contribution. Author ordering determined by coin flip.

[Paper] [Webpage]

Update: we released a newer version DrQ-v2, please check it out here.

Implementations in other frameworks: jax/flax.

Citation

If you use this repo in your research, please consider citing the paper as follows

@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}
}

Requirements

We assume you have access to a gpu that can run CUDA 9.2. Then, the simplest way to install all required dependencies is to create an anaconda environment by running

conda env create -f conda_env.yml

After the instalation ends you can activate your environment with

conda activate drq

Instructions

To train the DrQ agent on the Cartpole Swingup task run

python train.py env=cartpole_swingup

you can get the state-of-the-art performance in under 3 hours.

To reproduce the results from the paper run

python train.py env=cartpole_swingup batch_size=512 action_repeat=8

This will produce the runs folder, where all the outputs are going to be stored including train/eval logs, tensorboard blobs, and evaluation episode videos. To launch tensorboard run

tensorboard --logdir runs

The console output is also available in a form:

| train | E: 5 | S: 5000 | R: 11.4359 | D: 66.8 s | BR: 0.0581 | ALOSS: -1.0640 | CLOSS: 0.0996 | TLOSS: -23.1683 | TVAL: 0.0945 | AENT: 3.8132

a training entry decodes as

train - training episode
E - total number of episodes
S - total number of environment steps
R - episode return
D - duration in seconds
BR - average reward of a sampled batch
ALOSS - average loss of the actor
CLOSS - average loss of the critic
TLOSS - average loss of the temperature parameter
TVAL - the value of temperature
AENT - the actor's entropy

while an evaluation entry

| eval  | E: 20 | S: 20000 | R: 10.9356

contains

E - evaluation was performed after E episodes
S - evaluation was performed after S environment steps
R - average episode return computed over `num_eval_episodes` (usually 10)

The PlaNet Benchmark

DrQ demonstrates the state-of-the-art performance on a set of challenging image-based tasks from the DeepMind Control Suite (Tassa et al., 2018). We compare against PlaNet (Hafner et al., 2018), SAC-AE (Yarats et al., 2019), SLAC (Lee et al., 2019), CURL (Srinivas et al., 2020), and an upper-bound performance SAC States (Haarnoja et al., 2018). This follows the benchmark protocol established in PlaNet (Hafner et al., 2018). The PlaNet Benchmark

The Dreamer Benchmark

DrQ demonstrates the state-of-the-art performance on an extended set of challenging image-based tasks from the DeepMind Control Suite (Tassa et al., 2018), following the benchmark protocol from Dreamer (Hafner et al., 2019). We compare against Dreamer (Hafner et al., 2019) and an upper-bound performance SAC States (Haarnoja et al., 2018). The Dreamer Benchmark

Acknowledgements

We used kornia for data augmentation.

Popular Data Augmentation Projects
Popular Deep Learning Projects
Popular Data Processing Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Python
Jupyter Notebook
Deep Learning
Pytorch
Benchmark
Performance
Reinforcement Learning
Gym
Rl
Deep Reinforcement Learning
Data Augmentation
Mujoco
Deepmind
Actor Critic