CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
Alternatives To Curl
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
Cs Video Courses56,273
5 days ago17
List of Computer Science courses with video lectures.
Ray25,916801993 hours ago76June 09, 20222,905apache-2.0Python
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.
Applied Ml24,242
12 days ago3mit
📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.
Annotated_deep_learning_paper_implementations22,4641a month ago76June 27, 202217mitJupyter Notebook
🧑‍🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
D2l En18,049
a day ago101otherPython
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 400 universities from 60 countries including Stanford, MIT, Harvard, and Cambridge.
Ml Agents14,81512145 hours ago44April 01, 2022166otherC#
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
Tensor2tensor13,70182114 days ago79June 17, 2020589apache-2.0Python
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
Deep Learning Drizzle10,767
6 months ago6HTML
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
Tensorflow Tutorials8,644
2 years ago2mitJupyter Notebook
TensorFlow Tutorials with YouTube Videos
Amazon Sagemaker Examples8,437
8 hours ago801apache-2.0Jupyter Notebook
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
Alternatives To Curl
Select To Compare

Alternative Project Comparisons

CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning

This repository is the official implementation of CURL for the DeepMind control experiments. Atari experiments were done in a separate codebase available here. Our implementation of SAC is based on SAC+AE by Denis Yarats.


All of the dependencies are in the conda_env.yml file. They can be installed manually or with the following command:

conda env create -f conda_env.yml


To train a CURL agent on the cartpole swingup task from image-based observations run bash script/ from the root of this directory. The file contains the following command, which you can modify to try different environments / hyperparamters.

    --domain_name cartpole \
    --task_name swingup \
    --encoder_type pixel \
    --action_repeat 8 \
    --save_tb --pre_transform_image_size 100 --image_size 84 \
    --work_dir ./tmp \
    --agent curl_sac --frame_stack 3 \
    --seed -1 --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 10000 --batch_size 128 --num_train_steps 1000000 

In your console, you should see printouts that look like:

| train | E: 221 | S: 28000 | D: 18.1 s | R: 785.2634 | BR: 3.8815 | A_LOSS: -305.7328 | CR_LOSS: 190.9854 | CU_LOSS: 0.0000
| train | E: 225 | S: 28500 | D: 18.6 s | R: 832.4937 | BR: 3.9644 | A_LOSS: -308.7789 | CR_LOSS: 126.0638 | CU_LOSS: 0.0000
| train | E: 229 | S: 29000 | D: 18.8 s | R: 683.6702 | BR: 3.7384 | A_LOSS: -311.3941 | CR_LOSS: 140.2573 | CU_LOSS: 0.0000
| train | E: 233 | S: 29500 | D: 19.6 s | R: 838.0947 | BR: 3.7254 | A_LOSS: -316.9415 | CR_LOSS: 136.5304 | CU_LOSS: 0.0000

For reference, the maximum score for cartpole swing up is around 845 pts, so CURL has converged to the optimal score. This takes about an hour of training depending on your GPU.

Log abbreviation mapping:

train - training episode
E - total number of episodes 
S - total number of environment steps
D - duration in seconds to train 1 episode
R - mean episode reward
BR - average reward of sampled batch
A_LOSS - average loss of actor
CR_LOSS - average loss of critic
CU_LOSS - average loss of the CURL encoder

All data related to the run is stored in the specified working_dir. To enable model or video saving, use the --save_model or --save_video flags. For all available flags, inspect To visualize progress with tensorboard run:

tensorboard --logdir log --port 6006

and go to localhost:6006 in your browser. If you're running headlessly, try port forwarding with ssh.

For GPU accelerated rendering, make sure EGL is installed on your machine and set export MUJOCO_GL=egl. For environment troubleshooting issues, see the DeepMind control documentation.

Popular Reinforcement Learning Projects
Popular Deep Learning Projects
Popular Machine Learning Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Deep Learning
Reinforcement Learning
Deep Neural Networks
Deep Reinforcement Learning
Deep Learning Algorithms
Deep Q Network