Picture for Klaus Dorer

Klaus Dorer

RL-X: A Deep Reinforcement Learning Library for RoboCup

Add code
Oct 20, 2023
Nico Bohlinger, Klaus Dorer
Figure 1 for RL-X: A Deep Reinforcement Learning Library for RoboCup
Figure 2 for RL-X: A Deep Reinforcement Learning Library for RoboCup
Figure 3 for RL-X: A Deep Reinforcement Learning Library for RoboCup
Figure 4 for RL-X: A Deep Reinforcement Learning Library for RoboCup

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.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon