Magma Offenburg
Refine
Year of publication
Document Type
- Conference Proceeding (39)
- Bachelor Thesis (3)
- Contribution to a Periodical (1)
- Master's Thesis (1)
Conference Type
- Konferenzartikel (15)
- Sonstiges (14)
- Konferenz-Abstract (10)
Keywords
- RoboCup (26)
- Roboter (4)
- Deep Learning (2)
- Deep Reinforcement Learning (2)
- Machine Learning (2)
- Entscheidungslogik (1)
- Fußballroboter (1)
- Humanoid Robots (1)
- Humanoider Roboter (1)
- Hyperparameter (1)
Institute
- Fakultät Elektrotechnik und Informationstechnik (E+I) (bis 03/2019) (28)
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (16)
- IMLA - Institute for Machine Learning and Analytics (4)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (1)
- Fakultät Medien und Informationswesen (M+I) (bis 21.04.2021) (1)
- Fakultät Wirtschaft (W) (1)
- INES - Institut für nachhaltige Energiesysteme (1)
Open Access
- Open Access (37)
- Bronze (24)
- Closed Access (6)
- Grün (2)
- Closed (1)
- Diamond (1)
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.