OPUS 4 | Magma Offenburg

Magma Offenburg

44 search hits

1 to 10

Sort by

RL-X: A Deep Reinforcement Learning Library (Not Only) for RoboCup (2024)

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 4.5 speedups compared to well-known frameworks like Stable-Baselines3.

RL-X: A Deep Reinforcement Learning Libray (not only) for RoboCup (2023)

Bohlinger, Nico ; Dorer, Klaus

Learning Backswing Kicks with Deep Reinforcement Learning (2022)

Bohlinger, Nico ; Dorer, Klaus

Deep Reinforcement Multi-Directional Kick-Learning of a Simulated Robot with Toes (2021)

Weiler, David ; Dorer, Klaus

Learning a Walk Behavior Utilizing Toes From Scratch (2019)

Fischer, Jens ; Dorer, Klaus

Learning Model-Free Behaviors (2018)

Dorer, Klaus ; Baur, Martin ; Christmann, Kim ; Eppinger, Sebastian ; Fischer, Jens ; Liegibel, Pascal ; Schmider, Carmen

2D Strategy Simulator for 3D simulation (2017)

Fischer, Jens