rl_reach: Reproducible Reinforcement Learning Experiments for Robotic Reaching Tasks
This work addresses the problem of tedious hyperparameter tuning and configuration selection for researchers and practitioners working on robotic reaching tasks using reinforcement learning.
This paper introduces rl_reach, an open-source software package for reproducible reinforcement learning experiments in robotic reaching tasks. It provides a unified toolbox for comparing different training parameter sets, including environments, agents, hyperparameter optimization, and policy evaluation scripts.
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.