English
Related papers

Related papers: Finite Sample Analysis of LSTD with Random Project…

200 papers

Dimensionality reduction techniques play important roles in the analysis of big data. Traditional dimensionality reduction approaches, such as principal component analysis (PCA) and linear discriminant analysis (LDA), have been studied…

Machine Learning · Computer Science 2018-05-31 Haozhe Xie , Jie Li , Hanqing Xue

We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of…

Consider convex optimization problems subject to a large number of constraints. We focus on stochastic problems in which the objective takes the form of expected values and the feasible set is the intersection of a large number of convex…

Machine Learning · Statistics 2015-11-13 Mengdi Wang , Yichen Chen , Jialin Liu , Yuantao Gu

We consider large linear and nonlinear fixed point problems, and solution with proximal algorithms. We show that there is a close connection between two seemingly different types of methods from distinct fields: 1) Proximal iterations for…

Numerical Analysis · Computer Science 2019-09-05 Dimitri P. Bertsekas

We study the reinforcement learning (RL) problem in a constrained Markov decision process (CMDP), where an agent explores the environment to maximize the expected cumulative reward while satisfying a single constraint on the expected total…

We study reinforcement learning under model misspecification, where we do not have access to the true environment but only to a reasonably close approximation to it. We address this problem by extending the framework of robust MDPs to the…

Machine Learning · Computer Science 2017-11-10 Aurko Roy , Huan Xu , Sebastian Pokutta

Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability requires effective post-training. Reinforcement learning with verifiable rewards (RLVR) is a…

Computation and Language · Computer Science 2026-05-12 Zichao Yu , Shengze Xu , Bingqing Jiang , Wenyi Zhang , Difan Zou

Robust Markov decision processes (RMDPs) extend standard Markov decision processes (MDPs) to account for uncertainty in the transition probabilities. RMDPs have an uncertainty set that defines a set of possible transition functions, each of…

Logic in Computer Science · Computer Science 2026-04-30 Marnix Suilen , Guillermo A. Pérez

In this paper, we address learning problems for high dimensional data. Previously, oblivious random projection based approaches that project high dimensional features onto a random subspace have been used in practice for tackling…

Machine Learning · Computer Science 2016-12-07 Yi Xu , Haiqin Yang , Lijun Zhang , Tianbao Yang

Training data attribution (TDA) identifies which training examples most influenced a model's prediction. Influence function methods are a theoretically grounded family of TDA methods and exploit gradients. To overcome the scalability…

Machine Learning · Computer Science 2026-05-15 Shuangqi Li , Hieu Le , Jingyi Xu , Mathieu Salzmann

Recent breakthroughs both in reinforcement learning and trajectory optimization have made significant advances towards real world robotic system deployment. Reinforcement learning (RL) can be applied to many problems without needing any…

Robotics · Computer Science 2019-10-23 Guillaume Bellegarda , Katie Byl

Many sequential decision-making problems that are currently automated, such as those in manufacturing or recommender systems, operate in an environment where there is either little uncertainty, or zero risk of catastrophe. As companies and…

Machine Learning · Computer Science 2023-04-04 Marc Rigter

Abstract dynamic programming models are used to analyze $\lambda$-policy iteration with randomization algorithms. Particularly, contractive models with infinite policies are considered and it is shown that well-posedness of the…

Systems and Control · Electrical Eng. & Systems 2020-06-12 Yuchao Li , Karl H. Johansson , Jonas Mårtensson

We investigate the concept of Best Approximation for Feedforward Neural Networks (FNN) and explore their convergence properties through the lens of Random Projection (RPNNs). RPNNs have predetermined and fixed, once and for all, internal…

Machine Learning · Computer Science 2024-02-20 Gianluca Fabiani

Searching the space of policies directly for the optimal policy has been one popular method for solving partially observable reinforcement learning problems. Typically, with each change of the target policy, its value is estimated from the…

Artificial Intelligence · Computer Science 2007-05-23 Leonid Peshkin , Christian R. Shelton

Efficient and biologically plausible alternatives to backpropagation in neural network training remain a challenge due to issues such as high computational complexity and additional assumptions about neural networks, which limit scalability…

Machine Learning · Computer Science 2024-03-20 Zeliang Zhang , Jinyang Jiang , Zhuo Liu , Susan Liang , Yijie Peng , Chenliang Xu

We investigate the challenge of parametrizing policies for reinforcement learning (RL) in high-dimensional continuous action spaces. Our objective is to develop a multimodal policy that overcomes limitations inherent in the commonly-used…

Machine Learning · Computer Science 2023-07-21 Zhiao Huang , Litian Liang , Zhan Ling , Xuanlin Li , Chuang Gan , Hao Su

Deep reinforcement learning has demonstrated remarkable achievements across diverse domains such as video games, robotic control, autonomous driving, and drug discovery. Common methodologies in partially-observable domains largely lean on…

Machine Learning · Computer Science 2024-02-15 Michael Lanier , Ying Xu , Nathan Jacobs , Chongjie Zhang , Yevgeniy Vorobeychik

This paper presents two novel algorithms for approximately projecting symmetric matrices onto the Positive Semidefinite (PSD) cone using Randomized Numerical Linear Algebra (RNLA). Classical PSD projection methods rely on full-rank…

Optimization and Control · Mathematics 2024-10-28 Morgan Jones , James Anderson

In real-world applications with large state and action spaces, reinforcement learning (RL) typically employs function approximations to represent core components like the policies, value functions, and dynamics models. Although powerful…

Machine Learning · Computer Science 2026-01-29 Chenxiao Gao , Haotian Sun , Na Li , Dale Schuurmans , Bo Dai
‹ Prev 1 4 5 6 7 8 10 Next ›