EnvPool is a fast, asynchronous, and parallel RL environment library designed for scaling reinforcement learning experiments. Developed by SAIL at Singapore, it leverages C++ backend and Python frontend for extremely high-speed environment interaction, supporting thousands of environments running in parallel on a single machine. It's compatible with Gymnasium API and RLlib, making it suitable for scalable training pipelines.
Features
- Supports highly parallelized RL environment execution
- Uses C++ backend for ultra-fast simulation
- Compatible with Gym/Gymnasium and RLlib APIs
- Asynchronous stepping and reset for better throughput
- Supports a variety of classic control, Atari, and custom environments
- Easy integration with existing RL libraries for training
Categories
Reinforcement Learning LibrariesLicense
Apache License V2.0Follow EnvPool
Other Useful Business Software
Build Securely on Azure with Proven Frameworks
Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of EnvPool!