English
Related papers

Related papers: A Gauss-Newton Method for Markov Decision Processe…

200 papers

This paper addresses the problem of planning under uncertainty in large Markov Decision Processes (MDPs). Factored MDPs represent a complex state space using state variables and the transition model using a dynamic Bayesian network. This…

Artificial Intelligence · Computer Science 2011-06-10 C. Guestrin , D. Koller , R. Parr , S. Venkataraman

Markov decision processes (MDPs) are a popular model for performance analysis and optimization of stochastic systems. The parameters of stochastic behavior of MDPs are estimates from empirical observations of a system; their values are not…

Artificial Intelligence · Computer Science 2017-10-26 Dimitri Scheftelowitsch , Peter Buchholz , Vahid Hashemi , Holger Hermanns

Maximum mean discrepancy (MMD) has been widely employed to measure the distance between probability distributions. In this paper, we propose using MMD to solve continuous multi-objective optimization problems (MOPs). For solving MOPs, a…

Machine Learning · Computer Science 2025-05-21 Hao Wang , Chenyu Shi , Angel E. Rodriguez-Fernandez , Oliver Schütze

Natural gradient descent is an optimization method traditionally motivated from the perspective of information geometry, and works well for many applications as an alternative to stochastic gradient descent. In this paper we critically…

Machine Learning · Computer Science 2020-09-22 James Martens

Many machine learning models depend on solving a large scale optimization problem. Recently, sub-sampled Newton methods have emerged to attract much attention for optimization due to their efficiency at each iteration, rectified a weakness…

Optimization and Control · Mathematics 2016-09-06 Haishan Ye , Luo Luo , Zhihua Zhang

This paper proposes and justifies two globally convergent Newton-type methods to solve unconstrained and constrained problems of nonsmooth optimization by using tools of variational analysis and generalized differentiation. Both methods are…

Optimization and Control · Mathematics 2023-04-27 Pham Duy Khanh , Boris Mordukhovich , Vo Thanh Phat , Dat Ba Tran

Natural policy gradient (NPG) methods are among the most widely used policy optimization algorithms in contemporary reinforcement learning. This class of methods is often applied in conjunction with entropy regularization -- an algorithmic…

Machine Learning · Statistics 2022-09-13 Shicong Cen , Chen Cheng , Yuxin Chen , Yuting Wei , Yuejie Chi

In this paper, we introduce a quasi-Newton method optimized for efficiently solving quasi-linear elliptic equations and systems, with a specific focus on GPU-based computation. By approximating the Jacobian matrix with a combination of…

Numerical Analysis · Mathematics 2025-03-25 Wenrui Hao , Sun Lee , Xiangxiong Zhang

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

In this paper, we study Newton-conjugate gradient (Newton-CG) methods for minimizing a nonconvex function $f$ whose Hessian is $(H_f,\nu)$-H\"older continuous with modulus $H_f>0$ and exponent $\nu\in(0,1]$. Recently proposed Newton-CG…

Optimization and Control · Mathematics 2026-04-30 Ziyang Zeng , Junyu Zhang , Chuan He

The use of network Newton methods for the decentralized optimization of a sum cost distributed through agents of a network is considered. Network Newton methods reinterpret distributed gradient descent as a penalty method, observe that the…

Optimization and Control · Mathematics 2015-04-24 Aryan Mokhtari , Qing Ling , Alejandro Ribeiro

We consider deterministic Markov decision processes (MDPs) and apply max-plus algebra tools to approximate the value iteration algorithm by a smaller-dimensional iteration based on a representation on dictionaries of value functions. The…

Machine Learning · Computer Science 2019-06-21 Francis Bach

Markov decision processes (MDPs) describe sequential decision-making processes; MDP policies return for every state in that process an advised action. Classical algorithms can efficiently compute policies that are optimal with respect to,…

Logic in Computer Science · Computer Science 2025-05-23 Roman Andriushchenko , Milan Češka , Sebastian Junges , Filip Macák

Hessian information speeds convergence substantially in motion optimization. The better the Hessian approximation the better the convergence. But how good is a given approximation theoretically? How much are we losing? This paper addresses…

Robotics · Computer Science 2016-05-31 Nathan Ratliff , Marc Toussaint , Jeannette Bohg , Stefan Schaal

In this paper we provide faster algorithms for approximately solving discounted Markov Decision Processes in multiple parameter regimes. Given a discounted Markov Decision Process (DMDP) with $|S|$ states, $|A|$ actions, discount factor…

Data Structures and Algorithms · Computer Science 2020-12-24 Aaron Sidford , Mengdi Wang , Xian Wu , Yinyu Ye

In this paper, we consider a strongly convex finite-sum minimization problem over a decentralized network and propose a communication-efficient decentralized Newton's method for solving it. We first apply dynamic average consensus (DAC) so…

Optimization and Control · Mathematics 2022-10-04 Huikang Liu , Jiaojiao Zhang , Anthony Man-Cho So , Qing Ling

Markov Decision Processes (MDP) is an useful framework to cast optimal sequential decision making problems. Given any MDP the aim is to find the optimal action selection mechanism i.e., the optimal policy. Typically, the optimal policy…

Systems and Control · Computer Science 2014-03-18 Chandrashekar Lakshminarayanan , Shalabh Bhatnagar

We present a method for solving implicit (factored) Markov decision processes (MDPs) with very large state spaces. We introduce a property of state space partitions which we call epsilon-homogeneity. Intuitively, an epsilon-homogeneous…

Artificial Intelligence · Computer Science 2013-02-08 Thomas L. Dean , Robert Givan , Sonia Leach

In this paper, we propose new methods to efficiently solve convex optimization problems encountered in sparse estimation, which include a new quasi-Newton method that avoids computing the Hessian matrix and improves efficiency, and we prove…

Optimization and Control · Mathematics 2023-09-06 Ryosuke Shimmura , Joe Suzuki

Partially observable Markov decision processes (POMDPs) provide an elegant mathematical framework for modeling complex decision and planning problems in stochastic domains in which states of the system are observable only indirectly, via a…

Artificial Intelligence · Computer Science 2011-06-02 M. Hauskrecht