English
Related papers

Related papers: Models and algorithms for skip-free Markov decisio…

200 papers

We propose a vector linear programming formulation for a non-stationary, finite-horizon Markov decision process with vector-valued rewards. Pareto efficient policies are shown to correspond to efficient solutions of the linear program, and…

Optimization and Control · Mathematics 2025-06-02 Anas Mifrani , Dominikus Noll

We consider the batch (off-line) policy learning problem in the infinite horizon Markov Decision Process. Motivated by mobile health applications, we focus on learning a policy that maximizes the long-term average reward. We propose a…

Statistics Theory · Mathematics 2022-09-20 Peng Liao , Zhengling Qi , Runzhe Wan , Predrag Klasnja , Susan Murphy

This paper considers the optimal control of time varying continuous time Markov chains whose transition rates are themselves Markov processes. In one set of problems the solution of an ordinary differential equation is shown to determine…

Systems and Control · Computer Science 2015-09-02 Manish Gupta

We propose MDP-GapE, a new trajectory-based Monte-Carlo Tree Search algorithm for planning in a Markov Decision Process in which transitions have a finite support. We prove an upper bound on the number of calls to the generative models…

Machine Learning · Computer Science 2020-06-11 Anders Jonsson , Emilie Kaufmann , Pierre Ménard , Omar Darwiche Domingues , Edouard Leurent , Michal Valko

We present algorithms to effectively represent a set of Markov decision processes (MDPs), whose optimal policies have already been learned, by a smaller source subset for lifelong, policy-reuse-based transfer learning in reinforcement…

Artificial Intelligence · Computer Science 2016-05-03 M. M. Hassan Mahmud , Majd Hawasly , Benjamin Rosman , Subramanian Ramamoorthy

Information-theoretic principles for learning and acting have been proposed to solve particular classes of Markov Decision Problems. Mathematically, such approaches are governed by a variational free energy principle and allow solving MDP…

Artificial Intelligence · Computer Science 2016-04-08 Jordi Grau-Moya , Felix Leibfried , Tim Genewein , Daniel A. Braun

We consider zero-sum stochastic games with finite state and action spaces, perfect information, mean payoff criteria, without any irreducibility assumption on the Markov chains associated to strategies (multichain games). The value of such…

Optimization and Control · Mathematics 2012-08-03 Marianne Akian , Jean Cochet-Terrasson , Sylvie Detournay , Stéphane Gaubert

We study a discrete-time model where each packet has a cost of not being sent -- this cost might depend on the packet content. We study the tradeoff between the age and the cost where the sender is confined to packet-based strategies. The…

Information Theory · Computer Science 2022-10-24 Yunus Inan , Reka Inovan , Emre Telatar

In this paper we study a class of risk-sensitive Markovian control problems in discrete time subject to model uncertainty. We consider a risk-sensitive discounted cost criterion with finite time horizon. The used methodology is the one of…

Optimization and Control · Mathematics 2021-04-15 Tomasz R. Bielecki , Tao Chen , Igor Cialenco

We study a class of multi-stage stochastic programs, which incorporate modeling features from Markov decision processes (MDPs). This class includes structured MDPs with continuous action and state spaces. We extend policy graphs to include…

Machine Learning · Computer Science 2026-04-09 David P. Morton , Oscar Dowson , Bernardo K. Pagnoncelli

Coordination of distributed agents is required for problems arising in many areas, including multi-robot systems, networking and e-commerce. As a formal framework for such problems, we use the decentralized partially observable Markov…

Artificial Intelligence · Computer Science 2014-01-16 Daniel S. Bernstein , Christopher Amato , Eric A. Hansen , Shlomo Zilberstein

This paper investigates the optimization problem of an infinite stage discrete time Markov decision process (MDP) with a long-run average metric considering both mean and variance of rewards together. Such performance metric is important…

Optimization and Control · Mathematics 2020-08-11 Li Xia

Value Iteration is a widely used algorithm for solving Markov Decision Processes (MDPs). While previous studies have extensively analyzed its convergence properties, they primarily focus on convergence with respect to the infinity norm. In…

Machine Learning · Computer Science 2025-02-06 Arsenii Mustafin , Sebastien Colla , Alex Olshevsky , Ioannis Ch. Paschalidis

We present a new, tractable method for solving and analyzing risk-aware control problems over finite and infinite, discounted time-horizons where the dynamics of the controlled process are described as a martingale problem. Supposing…

Optimization and Control · Mathematics 2020-06-23 Jukka Isohätälä , William B. Haskell

Continuous-time Markov decision processes are an important class of models in a wide range of applications, ranging from cyber-physical systems to synthetic biology. A central problem is how to devise a policy to control the system in order…

Systems and Control · Computer Science 2016-06-01 Ezio Bartocci , Luca Bortolussi , Tomǎš Brázdil , Dimitrios Milios , Guido Sanguinetti

This tutorial describes recently developed general optimality conditions for Markov Decision Processes that have significant applications to inventory control. In particular, these conditions imply the validity of optimality equations and…

Optimization and Control · Mathematics 2016-06-06 Eugene A. Feinberg

We use Markov risk measures to formulate a risk-averse version of the undiscounted total cost problem for a transient controlled Markov process. We derive risk-averse dynamic programming equations and we show that a randomized policy may be…

Optimization and Control · Mathematics 2014-03-25 Ozlem Cavus , Andrzej Ruszczynski

This paper proposes an iterative distributionally robust model predictive control (MPC) scheme to solve a risk-constrained infinite-horizon optimal control problem. In each iteration, the algorithm generates a trajectory from the starting…

Optimization and Control · Mathematics 2023-08-23 Alireza Zolanvari , Ashish Cherukuri

Markov decision processes (MDPs) are standard models for probabilistic systems with non-deterministic behaviours. Long-run average rewards provide a mathematically elegant formalism for expressing long term performance. Value iteration (VI)…

Systems and Control · Computer Science 2017-09-01 Pranav Ashok , Krishnendu Chatterjee , Przemyslaw Daca , Jan Křetínský , Tobias Meggendorfer

Markov chains are the de facto finite-state model for stochastic dynamical systems, and Markov decision processes (MDPs) extend Markov chains by incorporating non-deterministic behaviors. Given an MDP and rewards on states, a classical…

Logic in Computer Science · Computer Science 2024-11-13 Krishnendu Chatterjee , Laurent Doyen