English
Related papers

Related papers: Factored Value Iteration Converges

200 papers

We consider inexact policy iteration methods for large-scale infinite-horizon discounted MDPs with finite spaces, a variant of policy iteration where the policy evaluation step is implemented inexactly using an iterative solver for linear…

Optimization and Control · Mathematics 2024-04-10 Matilde Gargiani , Robin Sieber , Efe Balta , Dominic Liao-McPherson , John Lygeros

We develop several new algorithms for learning Markov Decision Processes in an infinite-horizon average-reward setting with linear function approximation. Using the optimism principle and assuming that the MDP has a linear structure, we…

Machine Learning · Computer Science 2021-04-27 Chen-Yu Wei , Mehdi Jafarnia-Jahromi , Haipeng Luo , Rahul Jain

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

In this paper we propose a new iterative algorithm to solve the fair PCA (FPCA) problem. We start with the max-min fair PCA formulation originally proposed in [1] and derive a simple and efficient iterative algorithm which is based on the…

Machine Learning · Statistics 2023-05-11 Prabhu Babu , Petre Stoica

This note provides a simple example demonstrating that, if exact computations are allowed, the number of iterations required for the value iteration algorithm to find an optimal policy for discounted dynamic programming problems may grow…

Artificial Intelligence · Computer Science 2013-12-25 Eugene A. Feinberg , Jefferson Huang

Singular value decomposition (SVD) and matrix inversion are ubiquitous in scientific computing. Both tasks are computationally demanding for large scale matrices. Existing algorithms can approximatively solve these problems with a given…

Numerical Analysis · Mathematics 2026-01-28 Weiwei Xu , Weijie Shen , Zhengjian Bai , Chen Xu

We consider the exploration-exploitation dilemma in finite-horizon reinforcement learning (RL). When the state space is large or continuous, traditional tabular approaches are unfeasible and some form of function approximation is mandatory.…

Machine Learning · Computer Science 2023-09-11 Andrea Zanette , David Brandfonbrener , Emma Brunskill , Matteo Pirotta , Alessandro Lazaric

We propose a simple iterative (SI) algorithm for the maxcut problem through fully using an equivalent continuous formulation. It does not need rounding at all and has advantages that all subproblems have explicit analytic solutions, the cut…

Optimization and Control · Mathematics 2024-07-23 Sihong Shao , Dong Zhang , Weixi Zhang

The matrix factor model has drawn growing attention for its advantage in achieving two-directional dimension reduction simultaneously for matrix-structured observations. In this paper, we propose a simple iterative least squares algorithm…

Methodology · Statistics 2023-08-02 Yong He , Ran Zhao , Wen-Xin Zhou

In this paper, we study a mean-variance optimization problem in an infinite horizon discrete time discounted Markov decision process (MDP). The objective is to minimize the variance of system rewards with the constraint of mean performance.…

Optimization and Control · Mathematics 2017-08-24 Li Xia

Standard Markov decision process (MDP) and reinforcement learning algorithms optimize the policy with respect to the expected gain. We propose an algorithm which enables to optimize an alternative objective: the probability that the gain is…

Machine Learning · Computer Science 2023-03-06 Vincent Corlay , Jean-Christophe Sibel

We analyze a modified version of Nesterov accelerated gradient algorithm, which applies to affine fixed point problems with non self-adjoint matrices, such as the ones appearing in the theory of Markov decision processes with discounted or…

Optimization and Control · Mathematics 2021-07-05 Marianne Akian , Stéphane Gaubert , Zheng Qu , Omar Saadi

Model checking undiscounted reachability and expected-reward properties on Markov decision processes (MDPs) is key for the verification of systems that act under uncertainty. Popular algorithms are policy iteration and variants of value…

Logic in Computer Science · Computer Science 2023-01-25 Arnd Hartmanns , Sebastian Junges , Tim Quatmann , Maximilian Weininger

Filtering---estimating the state of a partially observable Markov process from a sequence of observations---is one of the most widely studied problems in control theory, AI, and computational statistics. Exact computation of the posterior…

Artificial Intelligence · Computer Science 2013-01-07 Bhaskara Marthi , Hanna Pasula , Stuart Russell , Yuval Peres

Entropy regularized algorithms such as Soft Q-learning and Soft Actor-Critic, recently showed state-of-the-art performance on a number of challenging reinforcement learning (RL) tasks. The regularized formulation modifies the standard RL…

Machine Learning · Statistics 2019-10-15 Elena Smirnova , Elvis Dohmatob

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

Machine Learning · Computer Science 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

We propose to perform mean-field variational inference (MFVI) in a rotated coordinate system that reduces correlations between variables. The rotation is determined by principal component analysis (PCA) of a cross-covariance matrix…

Computation · Statistics 2025-10-10 Yifan Chen , Sifan Liu

Vector Fitting (VF) is a popular method of constructing rational approximants that provides a least squares fit to frequency response measurements. In an earlier work, we provided an analysis of VF for scalar-valued rational functions and…

Numerical Analysis · Mathematics 2016-10-05 Zlatko Drmac , Serkan Gugercin , Christopher Beattie

We survey incremental methods for minimizing a sum $\sum_{i=1}^mf_i(x)$ consisting of a large number of convex component functions $f_i$. Our methods consist of iterations applied to single components, and have proved very effective in…

Systems and Control · Computer Science 2017-12-21 Dimitri P. Bertsekas

The online Markov decision process (MDP) is a generalization of the classical Markov decision process that incorporates changing reward functions. In this paper, we propose practical online MDP algorithms with policy iteration and…

Machine Learning · Computer Science 2015-10-16 Yao Ma , Hao Zhang , Masashi Sugiyama