Cargando…
On the convergence of projective-simulation–based reinforcement learning in Markov decision processes
In recent years, the interest in leveraging quantum effects for enhancing machine learning tasks has significantly increased. Many algorithms speeding up supervised and unsupervised learning were established. The first framework in which ways to exploit quantum resources specifically for the broader...
Autores principales: | Boyajian, W. L., Clausen, J., Trenkwalder, L. M., Dunjko, V., Briegel, H. J. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer International Publishing
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7644479/ https://www.ncbi.nlm.nih.gov/pubmed/33184611 http://dx.doi.org/10.1007/s42484-020-00023-9 |
Ejemplares similares
-
Projective simulation with generalization
por: Melnikov, Alexey A., et al.
Publicado: (2017) -
An immediate-return reinforcement learning for the atypical Markov decision processes
por: Pan, Zebang, et al.
Publicado: (2022) -
The Convergence of a Cooperation Markov Decision Process System
por: Mo, Xiaoling, et al.
Publicado: (2020) -
Markov processes: characterization and convergence
por: Ethier, Stewart N, et al.
Publicado: (2009) -
Simulation-based algorithms for Markov decision processes
por: Chang, Hyeong Soo, et al.
Publicado: (2013)