Antonin RAFFIN

A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.

Stable-Baselines tutorial for Journées Nationales de la Recherche en Robotique 2019

S-RL Toolbox: Reinforcement Learning (RL) and State Representation Learning (SRL) for Robotics

SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms

Implementation of reinforcement learning approach to make a car learn to drive smoothly in minutes

State Representation Learning (SRL) zoo with PyTorch - Part of S-RL Toolbox

A simple and robust serial communication protocol. It was designed for Arduino but can be used for other purposes (e.g. bluetooth, sockets). Implementation in C Arduino, C++, Python and Rust.

Tutorial: Tools for Robotic Reinforcement Learning, Hands-on RL for Robotics with EAGER and Stable-Baselines3

Deep Q-Network (DQN) and Fitted Q-Iteration (FQI) tutorial for RL Summer School 2023 and 2026

Stable-Baselines3 (SB3) reinforcement learning tutorial for the Reinforcement Learning Virtual School 2021.

Code used to train an augmented auto-encoder (aka denoising auto-encoder with more augmentations) for the DonkeyCar simulator.

A simple and robust serial communication protocol. It was designed for Arduino but can be used for other purposes (e.g. bluetooth, sockets). This is the Rust implementation.

A simple and robust serial communication protocol. It was designed for Arduino but can be used for other purposes (e.g. bluetooth, sockets). This is the Python implementation.

Blazingly fast implementation of the Datasaurus paper. Same Stats, Different Graphs.

Port of pybullet envs to gymnasium

A simple and robust serial communication protocol. It was designed for Arduino but can be used for other purposes (e.g. bluetooth, sockets). This is the C++ implementation.

A graph annotation tool using a flask server and javascript

OpenAI gym environment for donkeycar simulator

Policy gradient (PG) and direct policy search for RL Summer School 2026

Unified framework for robot learning built on NVIDIA Isaac Sim

Great resources for making Reinforcement Learning work in Real Life situations. Papers,projects and more.

advent-of-code-2022 with Rust, easy to read solutions

Easily create a beautiful website using Academic and Hugo

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

Python sample codes for robotics algorithms.

Personal Homepage

No description.

Implementation of the (μ/μ,λ)-Evolution Strategy (ES) with Search Path algorithm in C++

No description.

Conan - The open-source C and C++ package manager

No description.

conan.io reStructuredText documentation

No description.

notes for prompt engineering

No description.

No description.

Author's PyTorch implementation of TD7 for online and offline RL

No description.

A hyperparameter optimization framework

Live Neural Style Transfer with Pytorch and a Webcam

A toolkit for developing and comparing reinforcement learning algorithms.

Simulation for the Real Robot Challenge (https://real-robot-challenge.com)

Live face recognition using dlib and triplet loss. Webcam demo.

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR). Python2 compatible (branch python2)

A place to submit conda recipes before they become fully fledged conda-forge feedstocks

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

An OpenAI Gym environment for the Flappy Bird game

No description.

No description.

No description.

No description.

A guide to the perilous world of reinforcement learning.

Python library to use packages in OptunaHub

A simple FastAPI Server to run XTTSv2

Free and Open Source Alternative to Splitwise. Share expenses with your friends and family.

No description.

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

Open-source wheeled biped robots

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

DrQ-v2: Improved Data-Augmented Reinforcement Learning

Mastering Diverse Domains through World Models

Author's PyTorch implementation of TD3 for OpenAI gym tasks

Implementation of Truncated Quantile Critics method for continuous reinforcement learning. https://bayesgroup.github.io/tqc/

flake8 is a python tool that glues together pycodestyle, pyflakes, mccabe, and third-party plugins to check the style and quality of some python code.

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

Numerical Black-Box Optimization Benchmarking Framework

A collection of robotics simulation environments for reinforcement learning

No description.

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

Tutorials on how to use EAGERx

EAGERx is a physics engine abstraction layer for reinforcement learning. EAGERx allows switching between simulators and reality with a single line of code, supports action and observation processing and controller switching for resets.

The eagerx_gui package provides gui functionallity for EAGERx.

A procedural Blender pipeline for photorealistic training image generation

C++-based high-performance parallel environment execution engine for general RL environments.

Compare PPO implementation performance on microrts gym env

A data-driven deep reinforcement learning library as an out-of-the-box tool.

A minimalist environment for decision-making in autonomous driving

No description.

No description.

Real-Time High-Resolution Background Matting

Object Detection using YOLOv2 and PyTorch. Working webcam demo.

The Implementation of FastSpeech based on pytorch.

An educational resource to help anyone learn deep reinforcement learning. Tensorflow 2 version

Realtime Human Pose Estimation in Tensorflow with Webcam demo

OpenAI gym environment for donkeycar simulator

Guessing Game | Comixified Movies

End-to-end solution that transforms input video into a comic in just a few seconds

This provides a sandbox simulator for training a self-driving car. This uses Unity for simulation and Python with Keras and Tensorflow for training. Recently updated to work on Python 3.4+ and Keras 2+

Explore and find reinforcement learning environments in a list of 100+ open source environments.