arXiv subjects

Eugene A. Feinberg

Publications and source records attributed to Eugene A. Feinberg.

At least 19 recordsLinked to original sources

arXiv2026

Properties of Turnpike Functions for Discounted Finite Markov Decision Processes

This paper studies convergence times of the Value Iteration Algorithm (VIA) for discounted discrete-time Markov Decision Processes (MDPs) with finite state and action sets. For each discount factor, starting from a finite number of iterations, which is called the turnpike integer, the VIA generates deterministic optimal policies for infinite-horizon problems. Turnpike integers are viewed as functions of discount factors called turnpike functions. We design an algorithm to detect in strongly polynomial time whether a discount factor is irregular - at which the sets of optimal policies change. We then prove that a turnpike function is upper-semicontinuous and finitely-piecewise constant on any closed subinterval of [0,1) that does not contain irregular points. In particular, we prove that for small discount factors a turnpike function is bounded by the number of states and design an algorithm based on the VIA to solve an MDP for all small discount factors in strongly polynomial time.

math.OC↗

arXiv2026

Dynamically Augmented CVaR for MDPs

This paper studies optimization of Conditional Value-at-Risk (CVaR) for Markov Decision Processes (MDPs) with finite state and action sets. It introduces the Dynamically augmented CVaR (DCVaR) risk measure and provides an algorithm for its optimization. This paper investigates a specially defined Robust MDP (RMDP), in which the state space is augmented with the tail risk level. This RMDP, which we call the Dynamically augmented RMDP (DRMDP), was introduced to the literature for calculations of optimal CVaR values by value iteration more than ten years ago, but, as was understood later, these value iterations compute lower bounds of minimal static CVaRs. DCVaR is defined as a time consistent version of the static CVaR, and it is a lower bound of the static CVaR. It also can be considered as a dynamic version of the nested CVaR. This paper provides an algorithm constructing a policy optimizing DCVaR of total discounted costs. The correctness of this algorithm is proved by studying a special mass transfer problem. The results on RMDPs needed for this paper are provided in the appendix.

math.OC↗

arXiv2025

On Pioneering Works of Albert Shiryaev on Markov Decision Processes and Some Later Developments

This article is dedicated to three fundamental papers on Markov Decision Processes and on control with incomplete observations published by Albert Shiryaev approximately sixty years ago. One of these papers was coauthored with O.V. Viskov. We discuss some of the results and some of many rich ideas presented in these papers and survey some later developments. At the end we mention some recent studies of Albert Shiryaev on Kolmogorov's equations for jump Markov processes and on control of continuous-time jump Markov processes.

math.PR↗

arXiv2025

Continuity of Filters for Discrete-Time Control Problems Defined by Explicit Equations

Discrete time control systems whose dynamics and observations are described by stochastic equations are common in engineering, operations research, health care, and economics. For example, stochastic filtering problems are usually defined via stochastic equations. These problems can be reduced to Markov decision processes (MDPs) whose states are posterior state distributions, and transition probabilities for such MDPs are sometimes called filters. This paper investigates sufficient conditions on transition and observation functions for the original problems to guarantee weak continuity of the filter. Under mild conditions on cost functions, weak continuity implies the existence of optimal policies minimizing the expected total costs, the validity of optimality equations, and convergence of value iterations to optimal values. This paper uses recent results on weak continuity of filters for partially observable MDPs defined by transition and observation probabilities. It develops a criterion of weak continuity of transition probabilities and a sufficient condition for continuity in total variation of transition probabilities. The results are illustrated with applications to filtering problems.

math.OC↗

arXiv2025

Average-Cost MDPs with Infinite State and Action Sets: New Sufficient Conditions for Optimality Inequalities and Equations

This paper studies discrete-time average-cost infinite-horizon Markov decision processes (MDPs) with Borel state and action sets. It introduces new sufficient conditions for { the} validity of optimality inequalities and optimality equations for MDPs with weakly and setwise continuous transition probabilities. These inequalities and equations imply the existence of deterministic optimal policies.

math.OC↗

arXiv2023

Equivalent Conditions for Weak Continuity of Nonlinear Filters

This paper studies weak continuity of nonlinear filters. It is well-known that Borel measurability of transition probabilities for problems with incomplete state observations is preserved when the original discrete-time process is replaced with the process whose states are belief probabilities. It is also known that the similar preservation may not hold for weak continuity of transition probabilities. In this paper we show that the sufficient condition for weak continuity of transition probabilities for beliefs introduced by Kara, Saldi, and Yuksel (2019) is a necessary and sufficient condition for semi-uniform Feller continuity of transition probabilities. The property of semi-uniform Feller continuity was introduced in Feinberg, Kasyanov, and Zgurovsky (2021), and, if the original transition probability has this property, then the transition probability of the process, whose state is a pair consisting of the belief probability and observation, also has this property. Thus, this property implies weak continuity of nonlinear filters. This paper also reviews several necessary and sufficient conditions for semi-uniform Feller continuity.

math.OC↗

arXiv2023

Semi-Uniform Feller Stochastic Kernels

This paper studies transition probabilities from a Borel subset of a Polish space to a product of two Borel subsets of Polish spaces. For such transition probabilities it introduces and studies the property of semi-uniform Feller continuity. This paper provides several equivalent definitions of semi-uniform Feller continuity and establishes its preservation under integration. The motivation for this study came from the theory of Markov decision processes with incomplete information, and this paper provides fundamental results useful for this theory.

math.PR↗

arXiv2022

Markov Decision Processes with Incomplete Information and Semi-Uniform Feller Transition Probabilities

This paper deals with control of partially observable discrete-time stochastic systems. It introduces and studies Markov Decision Processes with Incomplete Information and with semi-uniform Feller transition probabilities. The important feature of these models is that their classic reduction to Completely Observable Markov Decision Processes with belief states preserves semi-uniform Feller continuity of transition probabilities. Under mild assumptions on cost functions, optimal policies exist, optimality equations hold, and value iterations converge to optimal values for these models. In particular, for Partially Observable Markov Decision Processes the results of this paper imply new and generalize several known sufficient conditions on transition and observation probabilities for weak continuity of transition probabilities for Markov Decision Processes with belief states, the existence of optimal policies, validity of optimality equations defining optimal policies, and convergence of value iterations to optimal values.

math.OC↗

arXiv2022

Epi-Convergence of Expectation Functions under Varying Measures and Integrands

For expectation functions on metric spaces, we provide sufficient conditions for epi-convergence under varying probability measures and integrands, and examine applications in the area of sieve estimators, mollifier smoothing, PDE-constrained optimization, and stochastic optimization with expectation constraints. As a stepping stone to epi-convergence of independent interest, we develop parametric Fatou's lemmas under mild integrability assumptions. In the setting of Suslin metric spaces, the assumptions are expressed in terms of Pasch-Hausdorff envelopes. For general metric spaces, the assumptions shift to semicontinuity of integrands also on the sample space, which then is assumed to be a metric space.

math.OC↗

arXiv2022

Continuity of Discounted Values and the Structure of Optimal Policies for Periodic-Review Inventory Control with Setup Costs

This paper proves continuity of value functions in discounted periodic-review single-commodity total-cost inventory control problems with \revision{continuous inventory levels,} fixed ordering costs, possibly bounded inventory storage capacity, and possibly bounded order sizes for finite and infinite horizons. In each of these constrained models, the finite and infinite-horizon value functions are continuous, there exist deterministic Markov optimal finite-horizon policies, and there exist stationary deterministic Markov optimal infinite-horizon policies. For models with bounded inventory storage and unbounded order sizes, this paper also characterizes the conditions under which $(s_t, S_t)$ policies are optimal in the finite horizon and an $(s,S)$ policy is optimal in the infinite horizon.

math.OC↗

arXiv2021

Solutions for Zero-Sum Two-Player Games with Noncompact Decision Sets and Unbounded Payoffs

This paper provides sufficient conditions for the existence of solutions for two-person zero-sum games with inf/sup-compact payoff functions and with possibly noncompact decision sets for both players. Payoff functions may be unbounded, and we do not assume any convexity/concavity-type conditions. For such games expected payoff may not exist for some pairs of strategies. The results of this paper imply several classic facts. The paper also provides sufficient conditions for the existence of a value and solutions for each player. The results of this paper are illustrated with the number guessing game.

math.OC↗

arXiv2021

Kolmogorov's Equations for Jump Markov Processes and their Applications to Control Problems

This paper describes the structure of solutions to Kolmogorov's equations for nonhomogeneous jump Markov processes and applications of these results to control of jump stochastic systems. These equations were studied by Feller (1940), who clarified in 1945 in the errata to that paper that some of its results covered only nonexplosive Markov processes. In this work, which is largely of a survey nature, the case of explosive processes is also considered. This paper is based on the invited talk presented by the authors at the conference "Chebyshev-200", and it describes the results of their joined studies with Manasa Mandava (1984-2019).

math.PR↗

arXiv2021

A Class of Solvable Markov Decision Models with Incomplete Information

This paper investigates natural conditions for the existence of optimal policies for a Markov decision process with incomplete information (MDPII) and with expected total costs. The MDPII is the classic model of a controlled stochastic process with incomplete state observations which is more general than Partially Observable Markov Decision Processes (POMDPs). For MDPIIs we introduce the notion of a semi-uniform Feller transition probability, which is stronger than the notion of a weakly continuous transition probability. We show that an MDPII has a semi-uniform Feller transition probability if and only if the corresponding belief MDP also has a semi-uniform Feller transition probability. This fact has several corollaries. In particular, it provides new and implies all known sufficient conditions for the existence of optimal policies for POMDPs with expected total costs

math.OC↗

arXiv2021

Continuity of Parametric Optima for Possibly Discontinuous Functions and Noncompact Decision Sets

This paper investigates continuity properties of value functions and solutions for parametric optimization problems. These problems are important in operations research, control, and economics because optimality equations are their particular cases. The classic fact, Berge's maximum theorem, gives sufficient conditions for continuity of value functions and upper semicontinuity of solution multifunctions. Berge's maximum theorem assumes that the objective function is continuous and the multifunction of feasible sets is compact-valued. These assumptions are not satisfied in many applied problems, which historically has limited the relevance of the theorem. This paper generalizes Berge's maximum theorem in three directions: (i) the objective function may not be continuous, (ii) the multifunction of feasible sets may not be compact-valued, and (iii) necessary and sufficient conditions are provided. To illustrate the main theorem, this paper provides applications to inventory control and to the analysis of robust optimization over possibly noncompact action sets and discontinuous objective functions.

math.OC↗

arXiv2021

Average Cost Markov Decision Processes with Semi-Uniform Feller Transition Probabilities

This paper studies average-cost Markov decision processes with semi-uniform Feller transition probabilities. This class of MDPs was recently introduced by the authors to study MDPs with incomplete information. This paper studies the validity of optimality inequalities, the existence of optimal policies, and the approximations of optimal policies by policies optimizing total discounted costs.

math.OC↗

arXiv2021

MDPs with Setwise Continuous Transition Probabilities

This paper describes the structure of optimal policies for infinite-state Markov Decision Processes with setwise continuous transition probabilities. The action sets may be noncompact. The objective criteria are either the expected total discounted and undiscounted costs or average costs per unit time. The analysis of optimality equations and inequalities is based on the optimal selection theorem for inf-compact functions introduced in this paper.

math.OC↗

arXiv2020

Sufficiency of Markov Policies for Continuous-Time Jump Markov Decision Processes

This paper extends to Continuous-Time Jump Markov Decision Processes (CTJMDP) the classic result for Markov Decision Processes stating that, for a given initial state distribution, for every policy there is a (randomized) Markov policy, which can be defined in a natural way, such that at each time instance the marginal distributions of state-action pairs for these two policies coincide. It is shown in this paper that this equality takes place for a CTJMDP if the corresponding Markov policy defines a nonexplosive jump Markov process. If this Markov process is explosive, then at each time instance the marginal probability, that a state-action pair belongs to a measurable set of state-action pairs, is not greater for the described Markov policy than the same probability for the original policy. These results are used in this paper to prove that for expected discounted total costs and for average costs per unit time, for a given initial state distribution, for each policy for a CTJMDP the described a Markov policy has the same or better performance.

math.OC↗

arXiv2020

Strong Polynomiality of the Value Iteration Algorithm for Computing Nearly Optimal Policies for Discounted Dynamic Programming

This note provides upper bounds on the number of operations required to compute by value iterations a nearly optimal policy for an infinite-horizon discounted Markov decision process with a finite number of states and actions. For a given discount factor, magnitude of the reward function, and desired closeness to optimality, these upper bounds are strongly polynomial in the number of state-action pairs, and one of the provided upper bounds has the property that it is a non-decreasing function of the value of the discount factor.

math.OC↗