English
Related papers

Related papers: Acceleration Operators in the Value Iteration Algo…

200 papers

Higher-order Markov chains play a very important role in many fields, ranging from multilinear PageRank to financial modeling. In this paper, we propose three accelerated higher-order power methods for computing the limiting probability…

Optimization and Control · Mathematics 2020-08-26 Gaohang Yu , Yi Zhou , Laishui Lv

In this paper, we propose, analyze and demonstrate a dynamic momentum method to accelerate power and inverse power iterations with minimal computational overhead. The method can be applied to real diagonalizable matrices, is provably…

Numerical Analysis · Mathematics 2024-07-08 Christian Austin , Sara Pollock , Yunrong Zhu

This note re-visits the rolling-horizon control approach to the problem of a Markov decision process (MDP) with infinite-horizon discounted expected reward criterion. Distinguished from the classical value-iteration approach, we develop an…

Optimization and Control · Mathematics 2022-06-07 Hyeong Soo Chang

We introduce a generic scheme for accelerating first-order optimization methods in the sense of Nesterov, which builds upon a new analysis of the accelerated proximal point algorithm. Our approach consists of minimizing a convex objective…

Optimization and Control · Mathematics 2015-10-27 Hongzhou Lin , Julien Mairal , Zaid Harchaoui

Recently, deep neural networks (DNNs) have shown advantages in accelerating optimization algorithms. One approach is to unfold finite number of iterations of conventional optimization algorithms and to learn parameters in the algorithms.…

Machine Learning · Computer Science 2021-04-23 Byung Hyun Lee , Se Young Chun

Many real-world applications, such as those in medical domains, recommendation systems, etc, can be formulated as large state space reinforcement learning problems with only a small budget of the number of policy changes, i.e., low…

Machine Learning · Computer Science 2021-01-05 Minbo Gao , Tianle Xie , Simon S. Du , Lin F. Yang

Novel advanced policy gradient (APG) methods, such as Trust Region policy optimization and Proximal policy optimization (PPO), have become the dominant reinforcement learning algorithms because of their ease of implementation and good…

Optimization and Control · Mathematics 2022-03-22 J. G. Dai , Mark Gluzman

This paper studies value iteration for infinite horizon contracting Markov decision processes under convexity assumptions and when the state space is uncountable. The original value iteration is replaced with a more tractable form and the…

Optimization and Control · Mathematics 2018-02-21 Jeremy Yee

This paper analyzes reinforcement learning (RL) algorithms for Markov decision processes (MDPs) under the average-reward criterion. We focus on Q-learning algorithms based on relative value iteration (RVI), which are model-free stochastic…

Machine Learning · Computer Science 2024-08-30 Yi Wan , Huizhen Yu , Richard S. Sutton

This paper introduces a unified framework for accelerated gradient methods through the variable and operator splitting (VOS). The operator splitting decouples the optimization process into simpler subproblems, and more importantly, the…

Optimization and Control · Mathematics 2025-05-08 Long Chen , Luo Hao , Jingrong Wei

Many problems in sequential decision making and stochastic control often have natural multiscale structure: sub-tasks are assembled together to accomplish complex goals. Systematically inferring and leveraging hierarchical structure,…

Artificial Intelligence · Computer Science 2012-12-06 Jake Bouvrie , Mauro Maggioni

We propose in this paper a unifying scheme for several algorithms from the literature dedicated to the solving of monotone inclusion problems involving compositions with linear continuous operators in infinite dimensional Hilbert spaces. We…

Optimization and Control · Mathematics 2017-05-08 Radu Ioan Bot , Ernö Robert Csetnek

We propose a new simple and natural algorithm for learning the optimal Q-value function of a discounted-cost Markov Decision Process (MDP) when the transition kernels are unknown. Unlike the classical learning algorithms for MDPs, such as…

Optimization and Control · Mathematics 2019-01-31 Dileep Kalathil , Vivek S. Borkar , Rahul Jain

The paper deals with finite-state Markov decision processes (MDPs) with integer weights assigned to each state-action pair. New algorithms are presented to classify end components according to their limiting behavior with respect to the…

Logic in Computer Science · Computer Science 2018-05-01 Christel Baier , Nathalie Bertrand , Clemens Dubslaff , Daniel Gburek , Ocan Sankur

In this paper, we show the convergence rates of posterior distributions of the model dynamics in a MDP for both episodic and continuous tasks. The theoretical results hold for general state and action space and the parameter space of the…

Statistics Theory · Mathematics 2019-07-23 Zhen Li , Eric Laber

This paper presents a novel accelerated distributed algorithm for unconstrained consensus optimization over static undirected networks. The proposed algorithm combines the benefits of acceleration from momentum, the robustness of the…

Optimization and Control · Mathematics 2024-05-15 Eduardo Sebastián , Mauro Franceschelli , Andrea Gasparri , Eduardo Montijano , Carlos Sagüés

We consider a discounted cost constrained Markov decision process (CMDP) policy optimization problem, in which an agent seeks to maximize a discounted cumulative reward subject to a number of constraints on discounted cumulative utilities.…

Optimization and Control · Mathematics 2024-11-21 Sihan Zeng , Thinh T. Doan , Justin Romberg

In a discounted reward Markov Decision Process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the…

Machine Learning · Computer Science 2019-06-17 Chandramouli Kamanchi , Raghuram Bharadwaj Diddigi , Shalabh Bhatnagar

We propose RUDDER, a novel reinforcement learning approach for delayed rewards in finite Markov decision processes (MDPs). In MDPs the Q-values are equal to the expected immediate reward plus the expected future rewards. The latter are…

We propose and analyze a temporal concatenation heuristic for solving large-scale finite-horizon Markov decision processes (MDP), which divides the MDP into smaller sub-problems along the time horizon and generates an overall solution by…

Optimization and Control · Mathematics 2022-06-22 Ruiyang Song , Kuang Xu