rl_reach: Reproducible Reinforcement Learning Experiments for Robotic Reaching Tasks

TL;DR

rl_reach is an open-source software toolkit that simplifies the process of conducting reproducible reinforcement learning experiments for robotic reaching tasks by integrating environments, agents, hyperparameter tuning, and evaluation tools.

Contribution

It introduces a comprehensive, easy-to-use platform that streamlines hyperparameter optimization and experiment reproducibility in reinforcement learning for robotics.

Findings

Facilitates quick comparison of training configurations

Supports customizable robotic reaching tasks

Enhances reproducibility of RL experiments

Abstract

Training reinforcement learning agents at solving a given task is highly dependent on identifying optimal sets of hyperparameters and selecting suitable environment input / output configurations. This tedious process could be eased with a straightforward toolbox allowing its user to quickly compare different training parameter sets. We present rl_reach, a self-contained, open-source and easy-to-use software package designed to run reproducible reinforcement learning experiments for customisable robotic reaching tasks. rl_reach packs together training environments, agents, hyperparameter optimisation tools and policy evaluation scripts, allowing its users to quickly investigate and identify optimal training configurations. rl_reach is publicly available at this URL: https://github.com/PierreExeter/rl_reach.