A Review of Nine Physics Engines for Reinforcement Learning Research

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kaup, Michael, Wolff, Cornelius, Hwang, Hyerim, Mayer, Julius, Bruni, Elia
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910574366949376
author Kaup, Michael
Wolff, Cornelius
Hwang, Hyerim
Mayer, Julius
Bruni, Elia
author_facet Kaup, Michael
Wolff, Cornelius
Hwang, Hyerim
Mayer, Julius
Bruni, Elia
contents We present a review of popular simulation engines and frameworks used in reinforcement learning (RL) research, aiming to guide researchers in selecting tools for creating simulated physical environments for RL and training setups. It evaluates nine frameworks (Brax, Chrono, Gazebo, MuJoCo, ODE, PhysX, PyBullet, Webots, and Unity) based on their popularity, feature range, quality, usability, and RL capabilities. We highlight the challenges in selecting and utilizing physics engines for RL research, including the need for detailed comparisons and an understanding of each framework's capabilities. Key findings indicate MuJoCo as the leading framework due to its performance and flexibility, despite usability challenges. Unity is noted for its ease of use but lacks scalability and simulation fidelity. The study calls for further development to improve simulation engines' usability and performance and stresses the importance of transparency and reproducibility in RL research. This review contributes to the RL community by offering insights into the selection process for simulation engines, facilitating informed decision-making.
format Preprint
id arxiv_https___arxiv_org_abs_2407_08590
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Review of Nine Physics Engines for Reinforcement Learning Research
Kaup, Michael
Wolff, Cornelius
Hwang, Hyerim
Mayer, Julius
Bruni, Elia
Artificial Intelligence
Machine Learning
Multiagent Systems
I.2.0
We present a review of popular simulation engines and frameworks used in reinforcement learning (RL) research, aiming to guide researchers in selecting tools for creating simulated physical environments for RL and training setups. It evaluates nine frameworks (Brax, Chrono, Gazebo, MuJoCo, ODE, PhysX, PyBullet, Webots, and Unity) based on their popularity, feature range, quality, usability, and RL capabilities. We highlight the challenges in selecting and utilizing physics engines for RL research, including the need for detailed comparisons and an understanding of each framework's capabilities. Key findings indicate MuJoCo as the leading framework due to its performance and flexibility, despite usability challenges. Unity is noted for its ease of use but lacks scalability and simulation fidelity. The study calls for further development to improve simulation engines' usability and performance and stresses the importance of transparency and reproducibility in RL research. This review contributes to the RL community by offering insights into the selection process for simulation engines, facilitating informed decision-making.
title A Review of Nine Physics Engines for Reinforcement Learning Research
topic Artificial Intelligence
Machine Learning
Multiagent Systems
I.2.0
url https://arxiv.org/abs/2407.08590