RL-X: A Deep Reinforcement Learning Library (Not Only) 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 4.5 speedups compared to well-known frameworks likeThis 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.…
| Document Type: | Conference Proceeding |
|---|---|
| Conference Type: | Konferenzartikel |
| Zitierlink: | https://opus.hs-offenburg.de/8905 | Bibliografische Angaben |
| Title (English): | RL-X: A Deep Reinforcement Learning Library (Not Only) for RoboCup |
| Conference: | RoboCup 2023, July 4 to 10, 2023, Bordeaux, Frankreich |
| Author: | Nico Bohlinger GND, Klaus DorerStaff MemberORCiDGND |
| Edition: | 1. |
| Year of Publication: | 2024 |
| Place of publication: | Cham |
| Publisher: | Springer |
| First Page: | 228 |
| Last Page: | 239 |
| Parent Title (English): | RoboCup 2023: Robot World Cup XXVI |
| Editor: | Cédric Buche, Alessandra Rossi, Marco Simões, Ubbo Visser |
| Volume: | LNCS 14140 |
| ISBN: | 978-3-031-55014-0 (Print) |
| ISBN: | 978-3-031-55015-7 (Online) |
| ISSN: | 0302-9743 (Print) |
| ISSN: | 1611-3349 (Elektronisch) |
| DOI: | https://doi.org/10.1007/978-3-031-55015-7_19 |
| Language: | English | Inhaltliche Informationen |
| Institutes: | Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) |
| Collections of the Offenburg University: | Bibliografie |
| Projekte / Magma Offenburg | |
| Research: | IMLA - Institute for Machine Learning and Analytics |
| Tag: | Deep Reinforcement Learning; RoboCup; Robotics; Simulation | Formale Angaben |
| Relevance for "Jahresbericht über Forschungsleistungen": | Konferenzbeitrag: h5-Index < 30 |
| Open Access: | Closed |
| Licence (German): |  Urheberrechtlich geschützt |