A Review of Nine Physics Engines for Reinforcement Learning Research
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| 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 |