Reinforcement Learning Experiments Running Efficiently over Widly Heterogeneous Computer Farms
- Borja Fernandez-Gauna 1
- Xabier Larrucea 1
- Manuel Graña 1
- 1 University of the Basque Country, UPV/EHU. Computational Intelligence Group (Leioa, Vizcaya)
- Hilde Pérez García (coord.)
- Lidia Sánchez González (coord.)
- Manuel Castejón Limas (coord.)
- Héctor Quintián Pardo (coord.)
- Emilio Corchado Rodríguez (coord.)
Éditorial: Springer Suiza
ISBN: 978-3-030-29859-3, 978-3-030-29858-6
Année de publication: 2019
Pages: 758-769
Congreso: Hybrid Artificial Intelligent Systems (14. 2019. León)
Type: Communication dans un congrès
Résumé
Researchers working with Reinforcement Learning typically face issues that severely hinder the efficiency of their research workflow. These issues include high computational requirements, numerous hyperparameters that must be set manually, and the high probability of failing a lot of times before success. In this paper, we present some of the challenges our research has faced and the way we have tackled successfully them in an innovative software platform.We provide some benchmarking results that show the improvements introduced by the new platform.