Refine
Document Type
- Article (unreviewed) (27) (remove)
Has Fulltext
- no (27)
Is part of the Bibliography
- yes (27) (remove)
Keywords
- Machine Learning (3)
- deep learning (2)
- Adversarial examples (1)
- Deep Leaning (1)
- Deep Learning (1)
- Deep Reinforcement Learning (1)
- Domenico Scarlatti (1)
- EU Timber Regulation (1)
- Explainable AI (1)
- Götz von Berlichingen (1)
Institute
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (27) (remove)
Open Access
- Open Access (23)
- Diamond (7)
- Bronze (5)
- Closed Access (4)
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.