Welcome to S-RL Toolbox’s documentation!

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

Github repository: https://github.com/araffin/robotics-rl-srl

Video: https://youtu.be/qNsHMkIsqJc

This repository was made to evaluate State Representation Learning methods using Reinforcement Learning. It integrates (automatic logging, plotting, saving, loading of trained agent) various RL algorithms (PPO, A2C, ARS, ACKTR, DDPG, DQN, ACER, CMA-ES, SAC, TRPO) along with different SRL methods (see SRL Repo) in an efficient way (1 Million steps in 1 Hour with 8-core cpu and 1 Titan X GPU).

We also release customizable Gym environments for working with simulation (Kuka arm, Mobile Robot in PyBullet, running at 250 FPS on a 8-core machine) and real robots (Baxter Robot, Robobo with ROS).

Main Features

  • 10 RL algorithms (Stable Baselines included)
  • logging / plotting / visdom integration / replay trained agent
  • hyperparameter search (hyperband, hyperopt)
  • integration with State Representation Learning (SRL) methods (for feature extraction)
  • visualisation tools (explore latent space, display action proba, live plot in the state space, …)
  • robotics environments to compare SRL methods
  • easy install using anaconda env or Docker images (CPU/GPU)

Related paper:


This documentation only gives an overview of the RL Toolbox, and provides some examples. However, for a complete list of possible argument, you have to use the --help argument. For example, you can try: python -m rl_baselines.train --help

Indices and tables