30 citations · 54 across the 10 of their papers we have counts for
13 papers
Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergence
Denis Zorba, David Šiška, Lukasz Szpruch
We provide theoretical guarantees for convergence of discrete-time policy mirror descent with inexact advantage functions updated using temporal difference (TD) learning for entrop…
Convergence of an actor-critic gradient flow for entropy regularised MDPs in general spaces
Denis Zorba, David Šiška, Lukasz Szpruch
We prove the stability and global convergence of a coupled actor-critic gradient flow for infinite-horizon and entropy-regularised Markov decision processes (MDPs) in continuous st…
Mirror descent for constrained stochastic control problems
Deven Sethi, David Šiška
Mirror descent is a well established tool for solving convex optimization problems with convex constraints. This article introduces continuous-time mirror descent dynamics for appr…
Ergodic optimal liquidations in DeFi
Jialun Cao, David Šiška
We address the liquidation problem arising from the credit risk management in decentralised finance (DeFi) by formulating it as an ergodic optimal control problem. In decentralised…
The Modified MSA, a Gradient Flow and Convergence
Deven Sethi, David Šiška
The modified Method of Successive Approximations (MSA) is an iterative scheme for approximating solutions to stochastic control problems in continuous time based on Pontryagin Opti…
Decaying derivative estimates for functions of solutions to non-autonomous SDEs
Maria Lefter, David Šiška, Łukasz Szpruch
We produce uniform and decaying bounds in time for derivatives of the solution to the backwards Kolmogorov equation associated to a stochastic processes governed by a time dependen…
Solving path dependent PDEs with LSTM networks and path signatures
Marc Sabate-Vidales, David Šiška, Lukasz Szpruch
Using a combination of recurrent neural networks and signature methods from the rough paths theory we design efficient algorithms for solving parametric families of path dependent…
A modified MSA for stochastic control problems
Bekzhan Kerimkulov, David Šiška, Łukasz Szpruch
The classical Method of Successive Approximations (MSA) is an iterative method for solving stochastic control problems and is derived from Pontryagin's optimality principle. It is…
Mean-Field Neural ODEs via Relaxed Optimal Control
Jean-François Jabir, David Šiška, Łukasz Szpruch
We develop a framework for the analysis of deep neural networks and neural ODE models that are trained with stochastic gradient algorithms. We do that by identifying the connection…
Weak Existence and Uniqueness for McKean-Vlasov SDEs with Common Noise
William R. P. Hammersley, David Šiška, Łukasz Szpruch
This paper concerns the McKean-Vlasov stochastic differential equation (SDE) with common noise. An appropriate definition of a weak solution to such an equation is developed. The i…
Exponential Convergence and stability of Howards's Policy Improvement Algorithm for Controlled Diffusions
B. Kerimkulov, D. Šiška, Ł. Szpruch
Optimal control problems are inherently hard to solve as the optimization must be performed simultaneously with updating the underlying system. Starting from an initial guess, Howa…
McKean-Vlasov SDEs under Measure Dependent Lyapunov Conditions
William Hammersley, David Šiška, Lukasz Szpruch
We prove the existence of weak solutions to McKean-Vlasov SDEs defined on a domain with continuous and unbounded coefficients that satisfy Lyapunov type…
Itô Formula for Processes Taking Values in Intersection of Finitely Many Banach Spaces
István Gyöngy, David Šiška
Motivated by applications to SPDEs we extend the Itô formula for the square of the norm of a semimartingale from Gyöngy and Krylov (Stochastics 6(3):153-173, 1982) to the ca…