This is a list of projects using stable-baselines. Please tell us, if you want your project to appear on this page ;)

Learning to drive in a day

Implementation of reinforcement learning approach to make a donkey car learn to drive. Uses DDPG on VAE features (reproducing paper from

Author: Roma Sokolkov (@r7vme)

Donkey Gym

OpenAI gym environment for donkeycar simulator.

Author: Tawn Kramer (@tawnkramer)

Self-driving FZERO Artificial Intelligence

Series of videos on how to make a self-driving FZERO artificial intelligence using reinforcement learning algorithms PPO2 and A2C.

Author: Lucas Thompson

S-RL Toolbox

S-RL Toolbox: Reinforcement Learning (RL) and State Representation Learning (SRL) for Robotics. Stable-Baselines was originally developped for this project.

Authors: Antonin Raffin, Ashley Hill, René Traoré, Timothée Lesort, Natalia Díaz-Rodríguez, David Filliat

Roboschool simulations training on Amazon SageMaker

“In this notebook example, we will make HalfCheetah learn to walk using the stable-baselines […]”

Author: Amazon AWS

MarathonEnvs + OpenAi.Baselines

Experimental - using OpenAI baselines with MarathonEnvs (ML-Agents)

Author: Joe Booth (@Sohojoe)

Learning to drive smoothly in minutes

Implementation of reinforcement learning approach to make a car learn to drive smoothly in minutes. Uses SAC on VAE features.

Making Roboy move with elegance

Project around Roboy, a tendon-driven robot, that enabled it to move its shoulder in simulation to reach a pre-defined point in 3D space. The agent used Proximal Policy Optimization (PPO) or Soft Actor-Critic (SAC) and was tested on the real hardware.

Authors: Alexander Pakakis, Baris Yazici, Tomas Ruiz
DockerHub image: deepandreinforced/rl:latest

Train a ROS-integrated mobile robot (differential drive) to avoid dynamic objects

The RL-agent serves as local planner and is trained in a simulator, fusion of the Flatland Simulator and the crowd simulator Pedsim. This was tested on a real mobile robot. The Proximal Policy Optimization (PPO) algorithm is applied.

Adversarial Policies: Attacking Deep Reinforcement Learning

Uses Stable Baselines to train adversarial policies that attack pre-trained victim policies in a zero-sum multi-agent environments. May be useful as an example of how to integrate Stable Baselines with Ray to perform distributed experiments and Sacred for experiment configuration and monitoring.

Authors: Adam Gleave, Michael Dennis, Neel Kant, Cody Wild

WaveRL: Training RL agents to perform active damping

Reinforcement learning is used to train agents to control pistons attached to a bridge to cancel out vibrations. The bridge is modeled as a one dimensional oscillating system and dynamics are simulated using a finite difference solver. Agents were trained using Proximal Policy Optimization. See presentation for environment detalis.

Authors: Jack Berkowitz

Fenics-DRL: Fluid mechanics and Deep Reinforcement Learning

Deep Reinforcement Learning is used to control the position or the shape of obstacles in different fluids in order to optimize drag or lift. Fenics is used for the Fluid Mechanics part, and Stable Baselines is used for the DRL.

Authors: Paul Garnier, Jonathan Viquerat, Aurélien Larcher, Elie Hachem

Air Learning: An AI Research Platform Algorithm Hardware Benchmarking of Autonomous Aerial Robots

Aerial robotics is a cross-layer, interdisciplinary field. Air Learning is an effort to bridge seemingly disparate fields.

Designing an autonomous robot to perform a task involves interactions between various boundaries spanning from modeling the environment down to the choice of onboard computer platform available in the robot. Our goal through building Air Learning is to provide researchers with a cross-domain infrastructure that allows them to holistically study and evaluate reinforcement learning algorithms for autonomous aerial machines. We use stable-baselines to train UAV agent with Deep Q-Networks and Proximal Policy Optimization algorithms.

Authors: Srivatsan Krishnan, Behzad Boroujerdian, William Fu, Aleksandra Faust, Vijay Janapa Reddi

Snake Game AI

AI to play the classic snake game. The game was trained using PPO2 available from stable-baselines and then exported to tensorflowjs to run directly on the browser

Author: Pedro Torres (@pedrohbtp)