Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Approximate policy iteration using regularized Bellman residuals minimization

Autor
Esposito, G.; Martin, M.
Tipus d'activitat
Article en revista
Revista
Journal of experimental and theoretical artificial intelligence
Data de publicació
2016
Volum
28
Número
1-2
Pàgina inicial
3
Pàgina final
12
DOI
https://doi.org/10.1080/0952813X.2015.1024494 Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/84681 Obrir en finestra nova
URL
http://www.tandfonline.com/doi/full/10.1080/0952813X.2015.1024494#.VS6nrJPcnv5 Obrir en finestra nova
Resum
Reinforcement Learning (RL) provides a general methodology to solve complex uncertain decision problems, which are very challenging in many real-world applications. RL problem is modeled as a Markov Decision Process (MDP) deeply studied in the literature. We consider Policy Iteration (PI) algorithms for RL which iteratively evaluate and improve control policies. In handling problems with continuous states or in very large state spaces, generalization is mandatory. Generalization property of RL a...
Citació
Esposito, G., Martin, M. Approximate policy iteration using regularized Bellman residuals minimization. "Journal of Experimental & Theoretical Artificial Intelligence", 2016, vol. 28, núm. 1-2, p. 3-12.
Paraules clau
Approximate Policy Iteration, Regression, Regularization, Reinforcement Learning, Support Vector Machine
Grup de recerca
IDEAI-UPC Intelligent Data Science and Artificial Intelligence
KEMLG - Grup d´Enginyeria del Coneixement i Aprenentatge Automàtic

Participants

Arxius