Deep neural networks algorithms for stochastic control problems on finite horizon, Part 2: numerical applications - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

Deep neural networks algorithms for stochastic control problems on finite horizon, Part 2: numerical applications

Résumé

This paper presents several numerical applications of deep learning-based algorithms that have been analyzed in [11]. Numerical and comparative tests using TensorFlow illustrate the performance of our different algorithms, namely control learning by performance iteration (algorithms NNcontPI and ClassifPI), control learning by hybrid iteration (algorithms Hybrid-Now and Hybrid-LaterQ), on the 100-dimensional nonlinear PDEs examples from [6] and on quadratic Backward Stochastic Differential equations as in [5]. We also provide numerical results for an option hedging problem in finance, and energy storage problems arising in the valuation of gas storage and in microgrid management.
Fichier principal
Vignette du fichier
Deepconsto-Partie2_Final.pdf (3.96 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01949221 , version 1 (12-12-2018)
hal-01949221 , version 2 (17-05-2019)
hal-01949221 , version 3 (25-01-2020)

Identifiants

Citer

Achref Bachouch, Côme Huré, Nicolas Langrené, Huyen Pham. Deep neural networks algorithms for stochastic control problems on finite horizon, Part 2: numerical applications. 2018. ⟨hal-01949221v1⟩
509 Consultations
1209 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More