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 exceedingly long training times. Baseline agents for major learning algorithms such as DDPG, PPO, SAC, TD3 and DSAC are provided too, along with a preliminary comparison in terms of training time and performance.

Asperti, A., Del Brutto, M. (2023). MicroRacer: A Didactic Environment for Deep Reinforcement Learning. Cham : Springer [10.1007/978-3-031-25599-1_18].

MicroRacer: A Didactic Environment for Deep Reinforcement Learning

Asperti, Andrea
;
2023

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 exceedingly long training times. Baseline agents for major learning algorithms such as DDPG, PPO, SAC, TD3 and DSAC are provided too, along with a preliminary comparison in terms of training time and performance.
2023
Machine Learning, Optimization, and Data Science. LOD 2022.
239
252
Asperti, A., Del Brutto, M. (2023). MicroRacer: A Didactic Environment for Deep Reinforcement Learning. Cham : Springer [10.1007/978-3-031-25599-1_18].
Asperti, Andrea; Del Brutto, Marco
File in questo prodotto:
File Dimensione Formato  
LOD_2022_Camera-Ready_2300.pdf

Open Access dal 10/03/2024

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 559.93 kB
Formato Adobe PDF
559.93 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/920351
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact