English
Related papers

Related papers: Low-rank State-action Value-function Approximation

200 papers

Low-rank modeling generally refers to a class of methods that solve problems by representing variables of interest as low-rank matrices. It has achieved great success in various fields including computer vision, data mining, signal…

Computer Vision and Pattern Recognition · Computer Science 2014-10-24 Xiaowei Zhou , Can Yang , Hongyu Zhao , Weichuan Yu

The primary challenge in solving kinetic equations, such as the Vlasov equation, is the high-dimensional phase space. In this context, dynamical low-rank approximations have emerged as a promising way to reduce the high computational cost…

Numerical Analysis · Mathematics 2021-07-28 Lukas Einkemmer , Ilon Joseph

In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning…

Machine Learning · Computer Science 2018-08-23 Dimitri P. Bertsekas

Value function factorization methods are commonly used in cooperative multi-agent reinforcement learning, with QMIX receiving significant attention. Many QMIX-based methods introduce monotonicity constraints between the joint action value…

Machine Learning · Computer Science 2025-04-11 Chang Huang , Shatong Zhu , Junqiao Zhao , Hongtu Zhou , Chen Ye , Tiantian Feng , Changjun Jiang

In this paper, we consider the problem of large scale multi agent reinforcement learning. Firstly, we studied the representation problem of the pairwise value function to reduce the complexity of the interactions among agents. Secondly, we…

Machine Learning · Computer Science 2020-01-13 Weiya Ren

Learning-based low rank approximation algorithms can significantly improve the performance of randomized low rank approximation with sketch matrix. With the learned value and fixed non-zero positions for sketch matrices from learning-based…

Machine Learning · Computer Science 2022-12-19 Tiejin Chen , Yicheng Tao

The QLP decomposition is one of the effective algorithms to approximate singular value decomposition (SVD) in numerical linear algebra. In this paper, we propose some single-pass randomized QLP decomposition algorithms for computing the…

Numerical Analysis · Mathematics 2020-11-30 Huan Ren , Zheng-Jian Bai

Variational approximation methods have proven to be useful for scaling Bayesian computations to large data sets and highly parametrized models. Applying variational methods involves solving an optimization problem, and recent research in…

Methodology · Statistics 2017-01-13 Victor M. -H. Ong , David J. Nott , Michael S. Smith

We describe an approximate dynamic programming method for stochastic control problems on infinite state and input spaces. The optimal value function is approximated by a linear combination of basis functions with coefficients as decision…

Optimization and Control · Mathematics 2012-12-07 Tyler H. Summers , Konstantin Kunz , Nikolaos Kariotoglou , Maryam Kamgarpour , Sean Summers , John Lygeros

Neural Network based approximations of the Value function make up the core of leading Policy Based methods such as Trust Regional Policy Optimization (TRPO) and Proximal Policy Optimization (PPO). While this adds significant value when…

Machine Learning · Computer Science 2024-06-03 Hari Srikanth

We propose an inexact variable-metric proximal point algorithm to accelerate gradient-based optimization algorithms. The proposed scheme, called QNing can be notably applied to incremental first-order methods such as the stochastic…

Machine Learning · Statistics 2019-01-30 Hongzhou Lin , Julien Mairal , Zaid Harchaoui

Our main contribution in this work is an empirical finding that random General Value Functions (GVFs), i.e., deep action-conditional predictions -- random both in what feature of observations they predict as well as in the sequence of…

Machine Learning · Computer Science 2021-11-09 Zeyu Zheng , Vivek Veeriah , Risto Vuorio , Richard Lewis , Satinder Singh

Dynamic Mode Decomposition (DMD) has emerged as a powerful tool for analyzing the dynamics of non-linear systems from experimental datasets. Recently, several attempts have extended DMD to the context of low-rank approximations. This…

Machine Learning · Statistics 2018-05-18 Patrick Héas , Cédric Herzet

Vision-Language Models (VLMs) are integral to tasks such as image captioning and visual question answering, but their high computational cost, driven by large memory footprints and processing time, limits their scalability and real-time…

Machine Learning · Computer Science 2025-10-21 Yutong Wang , Haiyu Wang , Sai Qian Zhang

Low-rank pre-training and fine-tuning have recently emerged as promising techniques for reducing the computational and storage costs of large neural networks. Training low-rank parameterizations typically relies on conventional optimizers…

Machine Learning · Computer Science 2025-10-31 Steffen Schotthöfer , Timon Klein , Jonas Kusch

We present a unified theoretical framework for parametric low-rank approximation, a research area devoted to the development of efficient algorithms that act as adaptive alternatives of traditional methods such as Singular Value…

Numerical Analysis · Mathematics 2025-09-22 Nicola Rares Franco

Discrete-action reinforcement learning algorithms often falter in tasks with high-dimensional discrete action spaces due to the vast number of possible actions. A recent advancement leverages value-decomposition, a concept from multi-agent…

Machine Learning · Computer Science 2024-03-11 David Ireland , Giovanni Montana

We consider a control problem for a finite-state Markov system whose performance is evaluated by a coherent Markov risk measure. For each policy, the risk of a state is approximated by a function of its features, thus leading to a…

Optimization and Control · Mathematics 2023-12-05 Andrzej Ruszczynski , Shangzhe Yang

Randomized value functions offer a promising approach towards the challenge of efficient exploration in complex environments with high dimensional state and action spaces. Unlike traditional point estimate methods, randomized value…

Machine Learning · Computer Science 2019-07-02 Ahmed Touati , Harsh Satija , Joshua Romoff , Joelle Pineau , Pascal Vincent

A primary interest in dynamic inverse problems is to identify the underlying temporal behaviour of the system from outside measurements. In this work we consider the case, where the target can be represented by a decomposition of spatial…

Numerical Analysis · Mathematics 2020-06-09 Simon Arridge , Pascal Fernsel , Andreas Hauptmann