S-RL Toolbox

Oct 10, 2018
Go to Project Site

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

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

Documentation: https://s-rl-toolbox.readthedocs.io

Paper: https://arxiv.org/abs/1809.09369

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)
Deep Learning Machine Learning Reinforcement Learning Python State Representation Learning Robotics
Avatar
Antonin Raffin
Research Engineer in Robotics and Machine Learning

Robots. Machine Learning. Blues Dance.

Related

Publications

Antonin Raffin, Ashley Hill, René Traoré, Timothée Lesort, Natalia Díaz-Rodríguez, David Filliat
January 2019 In SPiRL Workshop ICLR

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.

Preprint Code Project
Antonin Raffin, Ashley Hill, René Traoré, Timothée Lesort, Natalia Díaz-Rodríguez, David Filliat
September 2018 In Deep RL Workshop NIPS

S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning

State representation learning aims at learning compact representations from raw observations in robotics and control applications. Approaches used for this objective are auto-encoders, learning forward models, inverse dynamics or learning using generic priors on the state characteristics. However, the diversity in applications and methods makes the field lack standard evaluation datasets, metrics and tasks. This paper provides a set of environments, data generators, robotic control tasks, metrics and tools to facilitate iterative state representation learning and evaluation in reinforcement learning settings.

Preprint Code Project Video