envpool

We have hosted the application envpool in order to run this application in our online workstations with Wine or directly.

Quick description about envpool:

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

Programming Language: C++.
Categories: