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

Project Samples

Project Activity

See All Activity >

License

Apache License V2.0

Follow EnvPool

EnvPool Web Site

Other Useful Business Software
Project Planning and Management Software | Planview Icon
Project Planning and Management Software | Planview

Connect programs, projects, resources, and financials with business outcomes using portfolio management software from Planview.

Planview® Portfolios enables enterprises to accelerate strategic execution by seamlessly integrating business and technology planning, optimizing resources, and leveraging the power of embedded AI — Planview Anvi™ — to deliver breakthrough products, services, and customer experiences. This unified approach aligns strategy with execution, driving enhanced business performance across the organization.
Learn More
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of EnvPool!

Additional Project Details

Programming Language

C++

Related Categories

C++ Reinforcement Learning Libraries

Registered

2025-03-13