Quantum Markov Decision Processes: General Theory, Approximations, and Classes of Policies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Saldi, Naci, Sanjari, Sina, Yuksel, Serdar
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912032607961088
author Saldi, Naci
Sanjari, Sina
Yuksel, Serdar
author_facet Saldi, Naci
Sanjari, Sina
Yuksel, Serdar
contents In this paper, the aim is to develop a quantum counterpart to classical Markov decision processes (MDPs). Firstly, we provide a very general formulation of quantum MDPs with state and action spaces in the quantum domain, quantum transitions, and cost functions. Once we formulate the quantum MDP (q-MDP), our focus shifts to establishing the verification theorem that proves the sufficiency of Markovian quantum control policies and provides a dynamic programming principle. Subsequently, a comparison is drawn between our q-MDP model and previously established quantum MDP models (referred to as QOMDPs) found in the literature. Furthermore, approximations of q-MDPs are obtained via finite-action models, which can be formulated as QOMDPs. Finally, classes of open-loop and classical-state-preserving closed-loop policies for q-MDPs are introduced, along with structural results for these policies. In summary, we present a novel quantum MDP model aiming to introduce a new framework, algorithms, and future research avenues. We hope that our approach will pave the way for a new research direction in discrete-time quantum control.
format Preprint
id arxiv_https___arxiv_org_abs_2402_14649
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quantum Markov Decision Processes: General Theory, Approximations, and Classes of Policies
Saldi, Naci
Sanjari, Sina
Yuksel, Serdar
Quantum Physics
Systems and Control
Optimization and Control
In this paper, the aim is to develop a quantum counterpart to classical Markov decision processes (MDPs). Firstly, we provide a very general formulation of quantum MDPs with state and action spaces in the quantum domain, quantum transitions, and cost functions. Once we formulate the quantum MDP (q-MDP), our focus shifts to establishing the verification theorem that proves the sufficiency of Markovian quantum control policies and provides a dynamic programming principle. Subsequently, a comparison is drawn between our q-MDP model and previously established quantum MDP models (referred to as QOMDPs) found in the literature. Furthermore, approximations of q-MDPs are obtained via finite-action models, which can be formulated as QOMDPs. Finally, classes of open-loop and classical-state-preserving closed-loop policies for q-MDPs are introduced, along with structural results for these policies. In summary, we present a novel quantum MDP model aiming to introduce a new framework, algorithms, and future research avenues. We hope that our approach will pave the way for a new research direction in discrete-time quantum control.
title Quantum Markov Decision Processes: General Theory, Approximations, and Classes of Policies
topic Quantum Physics
Systems and Control
Optimization and Control
url https://arxiv.org/abs/2402.14649