Reinforcement Learning

Generalized State-Dependent Exploration for Deep Reinforcement Learning in Robotics

We extend the original state-dependent exploration (SDE) to apply deep reinforcement learning algorithms directly on real robots. The resulting method, gSDE, yields competitive results in simulation but outperforms the unstructured exploration on the real robot.

Stable Baselines3

A set of improved implementations of reinforcement learning algorithms in PyTorch.

RL Tutorial on Stable Baselines

Beginner tutorial on Stable Baselines library with colab notebooks

SRL - Stable Baselines Presentation

A talk about SRL, lessons learned from building Stable Baselines and short tutorial on how to use it

Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics

We evaluate the benefits of decoupling feature extraction from policy learning in robotics and propose a new way of combining state representation learning methods.

Learning to Drive Smoothly in Minutes

Learning to drive smoothly in minutes using reinforcement learning on a Donkey Car.

Learning to Drive Smoothly in Minutes

Learning to drive smoothly in minutes using reinforcement learning on a Donkey Car.

RL Baselines Zoo

A collection of 70+ pre-trained RL agents using Stable Baselines

S-RL Toolbox

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

Stable Baselines

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms