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

Nico Bohlinger, Klaus Dorer
10/20/2023
cs.ROcs.LG

Official code: nico-bohlinger/RL-X (268 stars, MIT, last commit 2026-05-03).

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.

View on arXivView PDF

Code Implementations(1)

nico-bohlinger/RL-XOfficial
MIT

A framework for Reinforcement Learning research.

26823Shell, PythonOct 14, 20225 months agoMIT
reinforcement-learning

Similar Papers

RobocupGym: A challenging continuous control benchmark in Robocup

87% match1 repo372024

Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes

85% match2024

RSL-RL: A Learning Library for Robotics Research

84% match1 repo2.8k2025

Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer

83% match2024

Planning the path with Reinforcement Learning: Optimal Robot Motion Planning in RoboCup Small Size League Environments

81% match1 repo42024

Solving Robotics Tasks with Prior Demonstration via Exploration-Efficient Deep Reinforcement Learning

81% match1 repo2025

Cite this paper

@article{bohlinger2023rlx,
  title  = {RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup},
  author = {Nico Bohlinger and Klaus Dorer},
  year   = {2023},
  eprint = {2310.13396},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.13396v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.13396.svg)](https://codeofpaper.com/paper/2310.13396)

Discussion