MicroRacer: a didactic environment for Deep Reinforcement Learning

TL;DR

MicroRacer is an accessible, open-source environment designed for teaching Deep Reinforcement Learning, enabling experimentation with various algorithms and hyperparameters without complex setup or long training times.

Contribution

It introduces a simple, calibrated environment for didactic purposes, including baseline agents for major algorithms and initial performance comparisons.

Findings

Baseline agents demonstrate varying training times and performance.

Environment facilitates easy experimentation for learners.

Provides a practical tool for Deep Reinforcement Learning education.

Abstract

MicroRacer is a simple, open source environment inspired by car racing especially meant for the didactics of Deep Reinforcement Learning. The complexity of the environment has been explicitly calibrated to allow users to experiment with many different methods, networks and hyperparameters settings without requiring sophisticated software or the need of exceedingly long training times. Baseline agents for major learning algorithms such as DDPG, PPO, SAC, TD2 and DSAC are provided too, along with a preliminary comparison in terms of training time and performance.