Controlled Martingale Problems And Their Markov Mimics

09/01/2023
by   Siva Athreya, et al.
0

In this article we prove under suitable assumptions that the marginals of any solution to a relaxed controlled martingale problem on a Polish space E can be mimicked by a Markovian solution of a Markov-relaxed controlled martingale problem. We also show how such `Markov mimics' can be obtained by relative entropy minimisation. We provide many examples where the above results can be applied.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/31/2015

Two Timescale Stochastic Approximation with Controlled Markov noise and Off-policy temporal difference learning

We present for the first time an asymptotic convergence analysis of two ...
research
12/06/2022

An Index Policy for Minimizing the Uncertainty-of-Information of Markov Sources

This paper focuses on the information freshness of finite-state Markov s...
research
04/23/2015

Stability of Stochastic Approximations with `Controlled Markov' Noise and Temporal Difference Learning

In this paper we present a `stability theorem' for stochastic approximat...
research
04/04/2023

A damped Kačanov scheme for the numerical solution of a relaxed p(x)-Poisson equation

The focus of the present work is the (theoretical) approximation of a so...
research
06/11/2019

Polymorphic Relaxed Noninterference

Information-flow security typing statically preserves confidentiality by...
research
06/11/2021

Relaxing Local Robustness

Certifiable local robustness, which rigorously precludes small-norm adve...
research
07/06/2022

Convergence of the Sinkhorn algorithm when the Schrödinger problem has no solution

The Sinkhorn algorithm is the most popular method for solving the Schröd...

Please sign up or login with your details

Forgot password? Click here to reset