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 4.5x 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 4.5x speedups compared to well-known frameworks like Stable-Baselines3.…
| Document Type: | Article (unreviewed) |
|---|---|
| Zitierlink: | https://opus.hs-offenburg.de/8439 | Bibliografische Angaben |
| Title (English): | RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup |
| Author: | Nico BohlingerGND, Klaus DorerStaff MemberORCiDGND |
| Year of Publication: | 2023 |
| Date of first Publication: | 2023/10/20 |
| First Page: | 1 |
| Last Page: | 12 |
| DOI: | https://doi.org/10.48550/arXiv.2310.13396 |
| Language: | English | Inhaltliche Informationen |
| Institutes: | Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) |
| Forschung / IMLA - Institute for Machine Learning and Analytics | |
| Institutes: | Bibliografie |
| Tag: | Deep Reinforcement Learning | Formale Angaben |
| Relevance: | Wiss. Zeitschriftenartikel unreviewed |
| Open Access: | Open Access |
| Bronze | |
| Licence (German): |  Urheberrechtlich geschützt |
| ArXiv Id: | http://arxiv.org/abs/2310.13396 |