D. Siska

Convergence of policy gradient for entropy regularized MDPs with neural network approximation in the mean-field regime pdf

David Siska, Lukasz Szpruch, Bekzhan Kerimkulov, 2022, ArXiv.

Gradient Flows for Regularized Stochastic Control Problems

L. Szpruch, D. Siska, 2020, ArXiv.

Mean-field Langevin dynamics and energy landscape of neural networks

Zhenjie Ren, David Siska, Lukasz Szpruch, 2019, Annales de l'Institut Henri Poincaré, Probabilités et Statistiques.

Exponential Convergence and stability of Howards's Policy Improvement Algorithm for Controlled Diffusions

L. Szpruch, B. Kerimkulov, D. Siska, 2018, 1812.07846.

Convergence of tamed Euler schemes for a class of stochastic evolution equations

István Gyöngy, David Šiška, Sotirios Sabanis, 2014, Stochastics and Partial Differential Equations: Analysis and Computations.

Convergence of policy gradient for entropy regularized MDPs with neural network approximation in the mean-field regime

L. Szpruch, B. Kerimkulov, J. Leahy, 2022, ICML.

Edinburgh Research Explorer Convergence of tamed Euler schemes for a class of stochastic evolution equations

S. Sabanis, D. Siska, 2017 .

Effect of Stop-Loss Reinsurance on Primary Insurer Solvency

B. Li, D. Siska, C. Constantinescu, 2022, Risks.

On a Full Discretisation for Nonlinear Second-Order Evolution Equations with Monotone Damping: Construction, Convergence, and Error Estimates

D. Siska, E. Emmrich, M. Thalhammer, 2015, Foundations of Computational Mathematics.

A Modified MSA for Stochastic Control Problems

L. Szpruch, B. Kerimkulov, D. Siska, 2021, Applied Mathematics & Optimization.