Home / Papers / RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup

RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup

DOI: 10.48550/arXiv.2310.13396Semantic Scholar

1 Citations•2023•

Nico Bohlinger, Klaus Dorer

journal unavailable

The new Deep Reinforcement Learning library RL-X provides a flexible and easy-to-extend codebase with self-contained single directory algorithms and its application to the RoboCup Soccer Simulation 3D League and classic DRL benchmarks is presented.

Abstract

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.