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

Antonin Raffin, Ashley Hill, René Traoré, Timothée Lesort, Natalia Díaz-Rodríguez +1 more
9/25/2018
cs.LGstat.ML

Official code: araffin/robotics-rl-srl (655 stars, MIT, PyTorch, last commit 2021-04-05).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

araffin/robotics-rl-srlOfficial100%
PyTorchMIT

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

65592Shell, PythonJan 18, 20185 years agoMIT
armbaselinesbaxter-robotgymkuka+6 more

Similar Papers

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

85% match1 repo6552019

State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping

85% match1 repo42023

Unsupervised State Representation Learning in Atari

85% match1 repo2592019

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

84% match2025

A Survey of State Representation Learning for Deep Reinforcement Learning

83% match2025

An Unbiased Look at Datasets for Visuo-Motor Pre-Training

83% match2023

Cite this paper

@article{raffin2018srl,
  title  = {S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning},
  author = {Antonin Raffin and Ashley Hill and René Traoré and Timothée Lesort and Natalia Díaz-Rodríguez and David Filliat},
  year   = {2018},
  eprint = {1809.09369},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1809.09369}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1809.09369.svg)](https://codeofpaper.com/paper/1809.09369)

Discussion