A Review of Nine Physics Engines for Reinforcement Learning Research
This review helps reinforcement learning researchers select simulation tools by providing a comparative analysis, though it is incremental as it synthesizes existing information without introducing new methods.
The paper reviewed nine physics simulation engines for reinforcement learning research, evaluating them on popularity, features, and usability, and found MuJoCo to be the leading framework in performance and flexibility, while Unity was noted for ease of use but lower scalability and fidelity.
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.