Compartir
Título
rl_reach: Reproducible reinforcement learning experiments for robotic reaching tasks
Autor
Facultad/Centro
Área de conocimiento
Título de la revista
Software Impacts
Cita Bibliográfica
Aumjaud, P., McAuliffe, D., Rodríguez Lera, F. J., & Cardiff, P. (2021). rl_reach: Reproducible reinforcement learning experiments for robotic reaching tasks[Formula presented]. Software Impacts, 8. https://doi.org/10.1016/J.SIMPA.2021.100061
Editorial
Elsevier
Fecha
2021
ISSN
2665-9638
Resumen
[EN] Training reinforcement learning agents at solving a given task is highly dependent on identifying optimal sets of hyperparameters and selecting suitable environment input/output configurations. This tedious process could be eased with a straightforward toolbox allowing its user to quickly compare different training parameter sets. We present rl_reach, a self-contained, open-source and easy-to-use software package designed to run reproducible reinforcement learning experiments for customisable robotic reaching tasks. rl_reach packs together training environments, agents, hyperparameter optimisation tools and policy evaluation scripts, allowing its users to quickly investigate and identify optimal training configurations. rl_reach is publicly available at this URL: https://github.com/PierreExeter/rl_reach
Materia
Palabras clave
Peer review
SI
URI
DOI
Aparece en las colecciones
- Artículos [5086]
Ficheros en el ítem
Tamaño:
1.430
xmlui.dri2xhtml.METS-1.0.size-megabytes
Formato:
Adobe PDF