English
Related papers

Related papers: Reward Algorithms for Semi-Markov Processes

200 papers

Safe reinforcement learning has been a promising approach for optimizing the policy of an agent that operates in safety-critical applications. In this paper, we propose an algorithm, SNO-MDP, that explores and optimizes Markov decision…

Machine Learning · Computer Science 2020-08-18 Akifumi Wachi , Yanan Sui

Probabilistic graphical models play a crucial role in machine learning and have wide applications in various fields. One pivotal subset is undirected graphical models, also known as Markov random fields. In this work, we investigate the…

Quantum Physics · Physics 2022-08-25 Liming Zhao , Lin-chun Wan , Ming-Xing Luo

We introduce the minimal maximally predictive models ({\epsilon}-machines) of processes generated by certain hidden semi-Markov models. Their causal states are either hybrid discrete-continuous or continuous random variables and…

Statistical Mechanics · Physics 2017-05-24 Sarah E. Marzen , James P. Crutchfield

In this paper, we consider the problem of optimization and learning for constrained and multi-objective Markov decision processes, for both discounted rewards and expected average rewards. We formulate the problems as zero-sum games where…

Optimization and Control · Mathematics 2021-03-05 Ather Gattami , Qinbo Bai , Vaneet Agarwal

The goal of this paper is to analyze distributional Markov Decision Processes as a class of control problems in which the objective is to learn policies that steer the distribution of a cumulative reward toward a prescribed target law,…

Optimization and Control · Mathematics 2026-02-09 Nicole Bäuerle , Athanasios Vasileiadis

Markov jump processes are continuous-time stochastic processes with a wide range of applications in both natural and social sciences. Despite their widespread use, inference in these models is highly non-trivial and typically proceeds via…

Machine Learning · Computer Science 2023-06-01 Patrick Seifner , Ramses J. Sanchez

This paper introduces a novel method of adding intrinsic bonuses to task-oriented reward function in order to efficiently facilitate reinforcement learning search. While various bonuses have been designed to date, they are analogous to the…

Machine Learning · Computer Science 2023-07-04 Taisuke Kobayashi

Motivated by entropic optimal transport, time reversal of Markov jump processes in $\mathbb{R}^n$ is investigated. Relying on an abstract integration by parts formula for the carr\'e du champ of a Markov process recently obtained by…

Probability · Mathematics 2022-09-05 Giovanni Conforti , Christian Léonard

We study episodic reinforcement learning in Markov decision processes when the agent receives additional feedback per step in the form of several transition observations. Such additional observations are available in a range of tasks…

Machine Learning · Computer Science 2020-05-11 Christoph Dann , Yishay Mansour , Mehryar Mohri , Ayush Sekhari , Karthik Sridharan

Markov Decision Processes (MDPs) have been used to formulate many decision-making problems in science and engineering. The objective is to synthesize the best decision (action selection) policies to maximize expected rewards (or minimize…

Optimization and Control · Mathematics 2015-07-07 Mahmoud El Chamie , Behcet Acikmese

Markov Decision Processes (MDPs) are a mathematical framework for modeling sequential decision making under uncertainty. The classical approaches for solving MDPs are well known and have been widely studied, some of which rely on…

Machine Learning · Computer Science 2018-05-18 Joshua R. Bertram , Xuxi Yang , Peng Wei

This study introduces a novel approach for learning mixtures of Markov chains, a critical process applicable to various fields, including healthcare and the analysis of web users. Existing research has identified a clear divide in…

Machine Learning · Computer Science 2024-05-27 Fabian Spaeh , Konstantinos Sotiropoulos , Charalampos E. Tsourakakis

In this paper we build on previous work which uses inferences techniques, in particular Markov Chain Monte Carlo (MCMC) methods, to solve parameterized control problems. We propose a number of modifications in order to make this approach…

Machine Learning · Computer Science 2012-05-14 Matthias Hoffman , Hendrik Kueck , Nando de Freitas , Arnaud Doucet

In a specific class of open quantum systems with finite and fixed numbers of collapsed quantum states, the semi-Markov process method is used to calculate the large deviations of the first passage time statistics. The core formula is an…

Statistical Mechanics · Physics 2024-10-10 Fei Liu , Shihao Xia , Shanhe Su

Stochastic processes find applications in modelling systems in a variety of disciplines. A large number of stochastic models considered are Markovian in nature. It is often observed that higher order Markov processes can model the data…

Probability · Mathematics 2021-04-13 Suryadeepto Nag

We study reinforcement learning for continuous-time Markov decision processes (MDPs) in the finite-horizon episodic setting. In contrast to discrete-time MDPs, the inter-transition times of a continuous-time MDP are exponentially…

Machine Learning · Computer Science 2023-10-04 Xuefeng Gao , Xun Yu Zhou

In the article the distributions of overjump functionals for almost semi-continuous processes on a finite irreducible Markov chain are considered.

Probability · Mathematics 2009-09-22 Ievgen Karnaukh

We analyze the convergence rate of various momentum-based optimization algorithms from a dynamical systems point of view. Our analysis exploits fundamental topological properties, such as the continuous dependence of iterates on their…

Optimization and Control · Mathematics 2021-04-13 Michael Muehlebach , Michael I. Jordan

Process mining is a well-established discipline of data analysis focused on the discovery of process models from information systems' event logs. Recently, an emerging subarea of process mining, known as stochastic process discovery, has…

Databases · Computer Science 2025-03-07 Anna Kalenkova , Lewis Mitchell , Matthew Roughan

Learning a near optimal policy in a partially observable system remains an elusive challenge in contemporary reinforcement learning. In this work, we consider episodic reinforcement learning in a reward-mixing Markov decision process (MDP).…

Machine Learning · Computer Science 2022-02-01 Jeongyeol Kwon , Yonathan Efroni , Constantine Caramanis , Shie Mannor
‹ Prev 1 4 5 6 7 8 10 Next ›