English
Related papers

Related papers: Transient Reward Approximation for Continuous-Time…

200 papers

We use the Reward Biased Maximum Likelihood Estimation (RBMLE) algorithm to learn optimal policies for constrained Markov Decision Processes (CMDPs). We analyze the learning regrets of RBMLE.

Optimization and Control · Mathematics 2021-05-31 Rahul Singh

We study the computational complexity of central analysis problems for One-Counter Markov Decision Processes (OC-MDPs), a class of finitely-presented, countable-state MDPs. OC-MDPs are equivalent to a controlled extension of (discrete-time)…

Computer Science and Game Theory · Computer Science 2009-09-11 Tomáš Brázdil , Václav Brožek , Kousha Etessami , Antonín Kučera , Dominik Wojtczak

Suppose there are $n$ Markov chains and we need to pay a per-step \emph{price} to advance them. The "destination" states of the Markov chains contain rewards; however, we can only get rewards for a subset of them that satisfy a…

Data Structures and Algorithms · Computer Science 2019-02-22 Anupam Gupta , Haotian Jiang , Ziv Scully , Sahil Singla

Markov chains are a common framework for individual-based state and time discrete models in ecology and evolution. Their use, however, is largely limited to systems with a low number of states, since the transition matrices involved pose…

Quantitative Methods · Quantitative Biology 2014-07-10 Katja Reichel , Valentin Bahier , Cédric Midoux , Jean-Pierre Masson , Solenn Stoeckel

We present a new algorithm based on posterior sampling for learning in Constrained Markov Decision Processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous…

Machine Learning · Computer Science 2024-05-30 Danil Provodin , Maurits Kaptein , Mykola Pechenizkiy

We consider Markov decision processes (MDPs) in which the transition probabilities and rewards belong to an uncertainty set parametrized by a collection of random variables. The probability distributions for these random parameters are…

Logic in Computer Science · Computer Science 2020-02-26 Murat Cubuktepe , Nils Jansen , Sebastian Junges , Joost-Pieter Katoen , Ufuk Topcu

We consider the task of generating draws from a Markov jump process (MJP) between two time-points at which the process is known. Resulting draws are typically termed bridges and the generation of such bridges plays a key role in…

Computation · Statistics 2019-01-31 Andrew Golightly , Chris Sherlock

We discuss a Monte Carlo Markov Chain (MCMC) procedure for the random sampling of some one-dimensional lattice paths with constraints, for various constraints. We show that an approach inspired by optimal transport allows us to bound…

Probability · Mathematics 2010-07-28 Lucas Gerin

In parameter estimation problems one computes a posterior distribution over uncertain parameters defined jointly by a prior distribution, a model, and noisy data. Markov Chain Monte Carlo (MCMC) is often used for the numerical solution of…

Numerical Analysis · Mathematics 2017-11-15 Matthias Morzfeld , Marcus S. Day , Ray W. Grout , George Shu Heng Pau , Stefan A. Finsterle , John B. Bell

We consider the reinforcement learning problem for the constrained Markov decision process (CMDP), which plays a central role in satisfying safety or resource constraints in sequential learning and decision-making. In this problem, we are…

Machine Learning · Computer Science 2025-11-19 Jiashuo Jiang , Yinyu Ye

In this paper we consider stopping problems for continuous-time Markov chains under a general risk-sensitive optimization criterion for problems with finite and infinite time horizon. More precisely our aim is to maximize the certainty…

Probability · Mathematics 2019-07-05 Nicole Bäuerle , Anton Popp

Verification of infinite-state Markov chains is still a challenge despite several fruitful numerical or statistical approaches. For decisive Markov chains, there is a simple numerical algorithm that frames the reachability probability as…

Logic in Computer Science · Computer Science 2024-09-30 Benoît Barbot , Patricia Bouyer , Serge Haddad

We consider partially observable Markov decision processes (POMDPs) with limit-average payoff, where a reward value in the interval [0,1] is associated to every transition, and the payoff of an infinite path is the long-run average of the…

Artificial Intelligence · Computer Science 2013-08-23 Krishnendu Chatterjee , Martin Chmelík

We introduce Dynamic Contextual Markov Decision Processes (DCMDPs), a novel reinforcement learning framework for history-dependent environments that generalizes the contextual MDP framework to handle non-Markov environments, where contexts…

Machine Learning · Computer Science 2023-05-19 Guy Tennenholtz , Nadav Merlis , Lior Shani , Martin Mladenov , Craig Boutilier

Information-theoretic quantities play a crucial role in understanding non-linear relationships between random variables and are widely used across scientific disciplines. However, estimating these quantities remains an open problem,…

Machine Learning · Computer Science 2025-02-28 Alberto Foresti , Giulio Franzese , Pietro Michiardi

We present a learning model predictive control (MPC) scheme for chance-constrained Markov jump systems with unknown switching probabilities. Using samples of the underlying Markov chain, ambiguity sets of transition probabilities are…

Optimization and Control · Mathematics 2023-01-06 Mathijs Schuurmans , Panagiotis Patrinos

Adaptive and interacting Markov Chains Monte Carlo (MCMC) algorithms are a novel class of non-Markovian algorithms aimed at improving the simulation efficiency for complicated target distributions. In this paper, we study a general…

Statistics Theory · Mathematics 2011-07-15 Gersende Fort , Eric Moulines , Pierre Priouret , Pierre Vandekerkhove

Supermarket models with different servers become a key in modeling resource management of stochastic networks, such as, computer networks, manufacturing systems and transportation networks. While these different servers always make analysis…

Performance · Computer Science 2016-04-06 Quan-Lin Li , Feifei Yang , Na Li

We consider partially observable Markov decision processes (POMDPs) with limit-average payoff, where a reward value in the interval [0,1] is associated to every transition, and the payoff of an infinite path is the long-run average of the…

Artificial Intelligence · Computer Science 2014-08-12 Krishnendu Chatterjee , Martin Chmelik

A continuous-time Markov chain rate change formula for simulation, model selection, filtering and theory is proven. It is used to develop Markov chain importance sampling, rejection sampling, branching particle filtering algorithms and…

Statistics Theory · Mathematics 2023-08-14 Michael A. Kouritzin