English
Related papers

Related papers: Practical Linear Value-approximation Techniques fo…

200 papers

Solving partially observable Markov decision processes (POMDPs) typically requires reasoning about the values of exponentially many state beliefs. Towards practical performance, state-of-the-art solvers use value bounds to guide this…

Artificial Intelligence · Computer Science 2025-02-11 Merlijn Krale , Wietze Koops , Sebastian Junges , Thiago D. Simão , Nils Jansen

This work investigates a new approach to find closed form analytical approximate solution of linear initial value problems. Classical Bernoulli polynomials have been used to derive a finite set of orthonormal polynomials and a finite…

Numerical Analysis · Mathematics 2020-07-27 Udaya Pratap Singh

We develop and analyse a first-order algorithm for the A-optimal experimental design problem. The problem is first presented as a special case of a parametric family of optimal design problems for which duality results and optimality…

Computation · Statistics 2013-11-12 Selin Damla Ahipasaoglu

We study an approach to policy selection for large relational Markov Decision Processes (MDPs). We consider a variant of approximate policy iteration (API) that replaces the usual value-function learning step with a learning step in policy…

Artificial Intelligence · Computer Science 2011-09-13 A. Fern , R. Givan , S. Yoon

Linear programming is the seminal optimization problem that has spawned and grown into today's rich and diverse optimization modeling and algorithmic landscape. This article provides an overview of the recent development of first-order…

Optimization and Control · Mathematics 2024-03-22 Haihao Lu

The continuous nature of belief states in POMDPs presents significant computational challenges in learning the optimal policy. In this paper, we consider an approach that solves a Partially Observable Reinforcement Learning (PORL) problem…

Machine Learning · Computer Science 2025-10-15 Ameya Anjarlekar , Rasoul Etesami , R Srikant

Real-world problems of operations research are typically high-dimensional and combinatorial. Linear programs are generally used to formulate and efficiently solve these large decision problems. However, in multi-period decision problems, we…

Machine Learning · Computer Science 2019-02-27 Wouter van Heeswijk , Han La Poutré

Many modern solvers and program analyzers rely on non-monotone reasoning (e.g. negation-as-failure, speculative updates, backtracking) for which classical monotone fixed-point methods do not apply. The general problem of finding the fixed…

Programming Languages · Computer Science 2026-05-11 Abdullah H. Rasheed , Vijay K. Garg

This paper shows that the optimal policy and value functions of a Markov Decision Process (MDP), either discounted or not, can be captured by a finite-horizon undiscounted Optimal Control Problem (OCP), even if based on an inexact model.…

Systems and Control · Electrical Eng. & Systems 2023-02-08 Arash Bahari Kordabad , Mario Zanon , Sebastien Gros

Factored Markov decision processes (MDPs) are a prominent paradigm within the artificial intelligence community for modeling and solving large-scale MDPs whose rewards and dynamics decompose into smaller, loosely interacting components.…

Optimization and Control · Mathematics 2024-04-03 Huikang Liu , Wolfram Wiesemann , Man-Chung Yue

We consider finite model approximations of discrete-time partially observed Markov decision processes (POMDPs) under the discounted cost criterion. After converting the original partially observed stochastic control problem to a fully…

Systems and Control · Computer Science 2017-10-20 Naci Saldi , Serdar Yüksel , Tamás Linder

Many large MDPs can be represented compactly using a dynamic Bayesian network. Although the structure of the value function does not retain the structure of the process, recent work has shown that value functions in factored MDPs can often…

Artificial Intelligence · Computer Science 2013-01-18 Daphne Koller , Ron Parr

We consider the problem of approximating a given matrix by a low-rank matrix so as to minimize the entrywise $\ell_p$-approximation error, for any $p \geq 1$; the case $p = 2$ is the classical SVD problem. We obtain the first provably good…

Data Structures and Algorithms · Computer Science 2017-05-19 Flavio Chierichetti , Sreenivas Gollapudi , Ravi Kumar , Silvio Lattanzi , Rina Panigrahy , David P. Woodruff

It is a challenging problem that solving the \textit{multivariate linear model} (MLM) $\mathbf{A}\mathbf{x}=\mathbf{b}$ with the $\ell_1 $-norm approximation method such that $||\mathbf{A}\mathbf{x}-\mathbf{b}||_1$, the $\ell_1$-norm of the…

Optimization and Control · Mathematics 2025-05-21 Zhi-Qiang Feng , Hong-Yan Zhanga , Ji Ma , Daniel Delahaye , Ruo-Shi Yang , Man Liang

We present a heuristic search algorithm for solving first-order MDPs (FOMDPs). Our approach combines first-order state abstraction that avoids evaluating states individually, and heuristic search that avoids evaluating all states. Firstly,…

Artificial Intelligence · Computer Science 2014-08-12 Eldar Karabaev , Olga Skvortsova

This paper addresses a fundamental issue central to approximation methods for solving large Markov decision processes (MDPs): how to automatically learn the underlying representation for value function approximation? A novel theoretically…

Artificial Intelligence · Computer Science 2012-07-09 Sridhar Mahadevan

We propose a principled kernel-based policy iteration algorithm to solve the continuous-state Markov Decision Processes (MDPs). In contrast to most decision-theoretic planning frameworks, which assume fully known state transition models, we…

Robotics · Computer Science 2020-06-04 Junhong Xu , Kai Yin , Lantao Liu

In this paper we present a review of the connections between classical algorithms for solving Markov Decision Processes (MDPs) and classical gradient-based algorithms in convex optimization. Some of these connections date as far back as the…

Optimization and Control · Mathematics 2021-11-29 Julien Grand-Clément

The paper investigates stochastic resource allocation problems with scarce, reusable resources and non-preemtive, time-dependent, interconnected tasks. This approach is a natural generalization of several standard resource management…

Machine Learning · Computer Science 2014-01-16 Balázs Csanád Csáji , László Monostori

Markov decision processes (MDPs) with rewards are a widespread and well-studied model for systems that make both probabilistic and nondeterministic choices. A fundamental result about MDPs is that their minimal and maximal expected rewards…

Logic in Computer Science · Computer Science 2024-11-26 Kevin Batz , Benjamin Lucien Kaminski , Christoph Matheja , Tobias Winkler
‹ Prev 1 8 9 10 Next ›