S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning
Machine Learning
2018-10-11 v2 Machine Learning
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.
Cite
@article{arxiv.1809.09369,
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},
journal= {arXiv preprint arXiv:1809.09369},
year = {2018}
}
Comments
Github repo: https://github.com/araffin/robotics-rl-srl Documentation: https://s-rl-toolbox.readthedocs.io/en/latest/