This paper presents the new Deep Reinforcement Learning (DRL) library RL-X and its application to the RoboCup Soccer Simulation 3D League and classic DRL benchmarks. RL-X provides a flexible and easy-to-extend codebase with self-contained single directory algorithms. Through the fast JAX-based implementations, RL-X can reach up to 4.5x speedups compared to well-known frameworks like Stable-Baselines3.

翻译：本文介绍了新型深度强化学习库RL-X及其在RoboCup足球仿真3D联赛和经典DRL基准测试中的应用。RL-X提供了灵活且易于扩展的代码库，其中包含自包含的单目录算法。通过基于JAX的快速实现，与Stable-Baselines3等知名框架相比，RL-X可实现高达4.5倍的加速效果。