CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms

TL;DR

CleanRL offers high-quality, single-file implementations of deep reinforcement learning algorithms, simplifying development, enabling scalability, and ensuring benchmarking for reliable performance across diverse environments.

Contribution

It introduces a comprehensive, single-file, open-source library for deep RL algorithms with tools for scaling, experiment tracking, and benchmarking.

Findings

Successful scaling to over 2000 machines using Docker and cloud services.

Benchmarking confirms the implementations' performance across various environments.

Single-file design enhances clarity and ease of use for researchers and developers.

Abstract

CleanRL is an open-source library that provides high-quality single-file implementations of Deep Reinforcement Learning algorithms. It provides a simpler yet scalable developing experience by having a straightforward codebase and integrating production tools to help interact and scale experiments. In CleanRL, we put all details of an algorithm into a single file, making these performance-relevant details easier to recognize. Additionally, an experiment tracking feature is available to help log metrics, hyperparameters, videos of an agent's gameplay, dependencies, and more to the cloud. Despite succinct implementations, we have also designed tools to help scale, at one point orchestrating experiments on more than 2000 machines simultaneously via Docker and cloud providers. Finally, we have ensured the quality of the implementations by benchmarking against a variety of environments. The source code of CleanRL can be found at https://github.com/vwxyzjn/cleanrl