accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

blog

Public repo for HF blog posts

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

course

The Hugging Face course on Transformers

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

decision-transformer

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

deep_rl

Single-file truly minimal implementation of state-of-the-art reinforcement learning algorithms.

desinformation

Dataviz project about désinformation

di-engine

OpenDILab Decision AI Engine

dmc_gym

drl-grasping

Deep Reinforcement Learning for Grasping

fake_repo_for_issue_form

first-contributions

🚀✨ Help beginners to contribute to open source projects

fqf-iqn-qrdqn.pytorch

PyTorch implementation of FQF, IQN and QR-DQN.

franka_panda_description

Franka Panda robot description, modified for providing gazebo simulation. Also includes more accurate dynamics values for KDL dynamics parameter estimations.

franka_python

Real OpenAI gym interface for Franka Emika Panda robot

gan_and_cgan

BE 2 GAN and cGAN

garage

A toolkit for reproducible reinforcement learning research.

go-explore-original

Code for Go-Explore: a New Approach for Hard-Exploration Problems

gym

A toolkit for developing and comparing reinforcement learning algorithms.

gym-continuous-maze

Continuous maze environment integrated with OpenAI/Gym

gym-docs

Code for Gym documentation website

gym-robotics

gymnasium

A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym)

highwayenv

A minimalist environment for decision-making in autonomous driving

huggingface_sb3

Additional code for Stable-baselines3 to load and upload models from the Hub.

image_classification_instructions

jat

lge