Sparad:
Bibliografiska uppgifter
Huvudupphovsmän: Szott, Szymon, Wojnar, Maksymilian, Rusek, Krzysztof, Ciężobka, Wojciech
Materialtyp: Recurso digital
Språk:engelska
Publicerad: Zenodo 2024
Ämnen:
Länkar:https://doi.org/10.5281/zenodo.11120099
Taggar: Lägg till en tagg
Inga taggar, Lägg till första taggen!
Innehållsförteckning:
  • <p><strong>Introducing Reinforced-lib:</strong> a lightweight Python library for the rapid development of RL solutions. It is open-source, prioritizes ease of use, provides comprehensive documentation, and offers both deep reinforcement learning (DRL) and classic non-neural agents. Built on <a href="https://jax.readthedocs.io/en/latest/" rel="nofollow">JAX</a>, it facilitates exporting trained models to embedded devices, and makes it great for research and prototyping with RL algorithms. Access to JAX's just-in-time (JIT) compilation ensures high-performance results.<br><br><span>This research was funded by the National Science Centre, Poland (2020/39/I/ST7/01457) and by the German Research Foundation (DFG DR 639/28-1). We gratefully acknowledge Polish high-performance computing infrastructure PLGrid (HPC Centers: ACK Cyfronet AGH) for providing computer facilities and support within computational grant no. PLG/2022/015838.</span></p>