English
Related papers

Related papers: Fixed Points of the Set-Based Bellman Operator

200 papers

We formalize the problem of maximizing the mean-payoff value with high probability while satisfying a parity objective in a Markov decision process (MDP) with unknown probabilistic transition function and unknown reward function. Assuming…

Artificial Intelligence · Computer Science 2018-08-24 Jan Křetínský , Guillermo A. Pérez , Jean-François Raskin

We associate to each iterated function system consisting of phi-max-contractions an operator (on the space of continuous functions from the shift space on the metric space corresponding to the system) having a unique fixed point whose image…

Classical Analysis and ODEs · Mathematics 2017-04-11 Flavian Georgescu , Radu Miculescu , Alexandru Mihail

In the renormalisation analysis of critical phenomena in quasi-periodic systems, a fundamental role is often played by fixed points of functional recurrences of the form \begin{equation*} f_{n}(x) = \sum_{i=1}^\ell a_i(x) f_{n_i}…

Dynamical Systems · Mathematics 2013-11-12 Paul Verschueren , Ben D. Mestel

In robust Markov decision processes (RMDPs), it is assumed that the reward and the transition dynamics lie in a given uncertainty set. By targeting maximal return under the most adversarial model from that set, RMDPs address performance…

Machine Learning · Computer Science 2024-02-13 Uri Gadot , Esther Derman , Navdeep Kumar , Maxence Mohamed Elfatihi , Kfir Levy , Shie Mannor

We study determinantal random point processes on a compact complex manifold X associated to an Hermitian metric on a line bundle over X and a probability measure on X. Physically, this setup describes a free fermion gas on X subject to a…

Complex Variables · Mathematics 2011-06-27 Robert J. Berman

Many distributional quantities in reinforcement learning are intrinsically joint across actions, including distributions of gaps and probabilities of superiority. However, the classical Markov decision process (MDP) formalism specifies only…

Machine Learning · Computer Science 2026-03-10 Ege C. Kaya , Mahsa Ghasemi , Abolfazl Hashemi

This paper is concerned with a data-driven technique for constructing finite Markov decision processes (MDPs) as finite abstractions of discrete-time stochastic control systems with unknown dynamics while providing formal closeness…

Systems and Control · Electrical Eng. & Systems 2022-06-30 Abolfazl Lavaei , Sadegh Soudjani , Emilio Frazzoli , Majid Zamani

In this paper, we establish some fixed point theorems in ordered partial metric spaces. An example is given to illustrate our obtained results.

General Topology · Mathematics 2016-10-05 Hassen Aydi

Markov Decision Processes (MDPs) are a popular class of models suitable for solving control decision problems in probabilistic reactive systems. We consider parametric MDPs (pMDPs) that include parameters in some of the transition…

Logic in Computer Science · Computer Science 2018-06-14 Sebastian Arming , Ezio Bartocci , Krishnendu Chatterjee , Joost-Pieter Katoen , Ana Sokolova

The planning domain has experienced increased interest in the formal synthesis of decision-making policies. This formal synthesis typically entails finding a policy which satisfies formal specifications in the form of some well-defined…

Artificial Intelligence · Computer Science 2021-11-30 George K. Atia , Andre Beckus , Ismail Alkhouri , Alvaro Velasquez

This paper discusses a general and useful stability principle which, roughly speaking, says that given a uniformly continuous function defined on an arbitrary metric space, if the function is bounded on the constraint set and we slightly…

Optimization and Control · Mathematics 2020-09-04 Daniel Reem , Simeon Reich , Alvaro De Pierro

This papers deals with the constrained discounted control of piecewise deterministic Markov process (PDMPs) in general Borel spaces. The control variable acts on the jump rate and transition measure, and the goal is to minimize the total…

Optimization and Control · Mathematics 2014-02-26 Oswaldo Costa , François Dufour

We introduce Multi-Environment Markov Decision Processes (MEMDPs) which are MDPs with a set of probabilistic transition functions. The goal in a MEMDP is to synthesize a single controller with guaranteed performances against all…

Logic in Computer Science · Computer Science 2014-12-04 Jean-François Raskin , Ocan Sankur

Motivated by the recent approach of Milman, Shabelman, and Yehudayoff \cite{MilmanShabelmanYehudayoff2025}, we establish, for $p\geq 1$, a complete characterization of the fixed points of the composition of the $L_p$-centroid operator and…

Functional Analysis · Mathematics 2026-05-26 Youjiang Lin , Sudan Xing

In this paper we are going to prove a very general fixed point theorem for mappings acting in partial metric spaces. In that theorem we impose some conditions on behavior of considered mappings on orbits and a condition relating orbits of…

General Topology · Mathematics 2023-12-27 Dariusz Bugajewski , Piotr Maćkowiak

This paper studies parametric Markov decision processes (pMDPs), an extension to Markov decision processes (MDPs) where transitions probabilities are described by polynomials over a finite set of parameters. Fixing values for all parameters…

Logic in Computer Science · Computer Science 2019-04-03 Tobias Winkler , Sebastian Junges , Guillermo A. Pérez , Joost-Pieter Katoen

We establish three major fixed-point theorems for functions satisfying an odd power type contractive condition in G-metric spaces. We first consider the case of a single mapping, followed by that of a triplet of mappings and we conclude by…

General Topology · Mathematics 2017-09-25 Yaé Ulrich Gaba , Collins Amburo Agyingi

We provide some new estimates for Bellman type functions for the dyadic maximal opeator on $R^n$ and of maximal operators on martingales related to weighted spaces. Using a type of symmetrization principle, introduced for the dyadic maximal…

Functional Analysis · Mathematics 2015-11-24 Antonios D. Melas , Eleftherios N. Nikolidakis , Dimitrios Cheliotis

The distributionally robust Markov Decision Process (MDP) approach asks for a distributionally robust policy that achieves the maximal expected total reward under the most adversarial distribution of uncertain parameters. In this paper, we…

Systems and Control · Computer Science 2018-10-10 Zhi Chen , Pengqian Yu , William B. Haskell

In this paper we consider an infinite time horizon risk-sensitive optimal stopping problem for a Feller--Markov process with an unbounded terminal cost function. We show that in the unbounded case an associated Bellman equation may have…

Optimization and Control · Mathematics 2022-11-01 Damian Jelito , Łukasz Stettner