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

Antonin Raffin; Ashley Hill; René Traoré; Timothée Lesort; Natalia Díaz-Rodríguez; David Filliat

Conference papers

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

Antonin Raffin ^{1, 2} Ashley Hill ^{1, 2} René Traoré ^{1, 2} Timothée Lesort ^{1, 3, 2} Natalia Díaz-Rodríguez ^{1, 2} David Filliat ^{1, 2}

1 U2IS - Unité d'Informatique et d'Ingénierie des Systèmes

2 Flowers - Flowing Epigenetic Robots and Systems

Inria Bordeaux - Sud-Ouest

3 Thales Research and Technology [Palaiseau]

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.

Keywords : state representation learning robotic priors reinforcement learning Deep learning

Document type :

Conference papers

Domain :

Computer Science [cs] / Robotics [cs.RO]

Complete list of metadata

https://hal.archives-ouvertes.fr/hal-01931713
Contributor : David Filliat Connect in order to contact the contributor
Submitted on : Thursday, November 29, 2018 - 9:56:25 AM
Last modification on : Wednesday, May 11, 2022 - 3:20:03 PM

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

File

Identifiers

Collections

Citation

Export

Metrics

103

196

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

File

Identifiers

Collections

Citation

Export

Share

Metrics

103

196