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

TL;DR

This paper introduces a comprehensive toolbox with environments, datasets, and metrics to standardize and facilitate the evaluation of state representation learning methods in robotics and control tasks.

Contribution

It provides a standardized set of environments, datasets, and evaluation tools to advance research in state representation learning for reinforcement learning applications.

Findings

Provides a versatile toolkit for state representation learning evaluation.

Facilitates comparison of different methods using common benchmarks.

Supports iterative development and assessment in robotics and control tasks.

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.