中文
相关论文

相关论文: Representation of Reinforcement Learning Policies …

200 篇论文

Kernel methods approximate nonlinear maps in a data-driven manner by projecting the target map onto a finite-dimensional Hilbert space called the solution space. Traditionally, this space is a subspace of a fixed ambient reproducing kernel…

数值分析 · 数学 2026-01-30 Tamás Dózsa , Andrea Angino , Zoltán Szabó , József Bokor , Matthias Voigt

In this paper we combine the theory of reproducing kernel Hilbert spaces with the field of collocation methods to solve boundary value problems with special emphasis on reproducing property of kernels. From the reproducing property of…

数值分析 · 数学 2019-03-26 Babak Azarnavid , Mahdi Emamjome , Mohammad Nabati , Saeid Abbasbandy

In this paper, we introduce a new distribution regression model for probability distributions. This model is based on a Reproducing Kernel Hilbert Space (RKHS) regression framework, where universal kernels are built using Wasserstein…

统计理论 · 数学 2019-10-07 Thi Thien Trang Bui , J-M Loubes , Laurent Risser , Patricia Balaresque

For safely applying reinforcement learning algorithms on high-dimensional nonlinear dynamical systems, a simplified system model is used to formulate a safe reinforcement learning framework. Based on the simplified system model, a…

机器人学 · 计算机科学 2021-09-09 Zhehua Zhou , Ozgur S. Oguz , Marion Leibold , Martin Buss

Many recurrent neural network machine learning paradigms can be formulated using state-space representations. The classical notion of canonical state-space realization is adapted in this paper to accommodate semi-infinite inputs so that it…

最优化与控制 · 数学 2021-08-12 Lyudmila Grigoryeva , Juan-Pablo Ortega

Kernel methods, being supported by a well-developed theory and coming with efficient algorithms, are among the most popular and successful machine learning techniques. From a mathematical point of view, these methods rest on the concept of…

机器学习 · 统计学 2023-03-20 Christian Fiedler , Michael Herty , Michael Rom , Chiara Segala , Sebastian Trimpe

This paper addresses the problem of model-free reinforcement learning for Robust Markov Decision Process (RMDP) with large state spaces. The goal of the RMDP framework is to find a policy that is robust against the parameter uncertainties…

机器学习 · 计算机科学 2021-02-15 Kishan Panaganti , Dileep Kalathil

Reinforcement learning methods trained on few environments rarely learn policies that generalize to unseen environments. To improve generalization, we incorporate the inherent sequential structure in reinforcement learning into the…

机器学习 · 计算机科学 2021-03-19 Rishabh Agarwal , Marlos C. Machado , Pablo Samuel Castro , Marc G. Bellemare

The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representations learned purely by the reinforcement learning loss can…

机器学习 · 计算机科学 2024-02-12 Somjit Nath , Rushiv Arora , Samira Ebrahimi Kahou

Reinforcement learning (RL) combines a control problem with statistical estimation: The system dynamics are not known to the agent, but can be learned through experience. A recent line of research casts `RL as inference' and suggests a…

机器学习 · 计算机科学 2020-11-05 Brendan O'Donoghue , Ian Osband , Catalin Ionescu

Weighted log-rank tests are arguably the most widely used tests by practitioners for the two-sample problem in the context of right-censored data. Many approaches have been considered to make weighted log-rank tests more robust against a…

统计方法学 · 统计学 2020-05-01 Tamara Fernandez , Nicolas Rivera

Replication of experimental results has been a challenge faced by many scientific disciplines, including the field of machine learning. Recent work on the theory of machine learning has formalized replicability as the demand that an…

机器学习 · 计算机科学 2026-04-15 Eric Eaton , Marcel Hussing , Michael Kearns , Aaron Roth , Sikata Bela Sengupta , Jessica Sorrell

We study approaches for compressing the empirical measure in the context of finite dimensional reproducing kernel Hilbert spaces (RKHSs). In this context, the empirical measure is contained within a natural convex set and can be…

机器学习 · 统计学 2024-08-29 Steffen Grünewälder

For many machine learning problem settings, particularly with structured inputs such as sequences or sets of objects, a distance measure between inputs can be specified more naturally than a feature representation. However, most standard…

机器学习 · 统计学 2018-05-28 Lingfei Wu , Ian En-Hsu Yen , Fangli Xu , Pradeep Ravikumar , Michael Witbrock

We propose a hierarchical learning strategy aimed at generating sparse representations and associated models for large noisy datasets. The hierarchy follows from approximation spaces identified at successively finer scales. For promoting…

机器学习 · 计算机科学 2020-06-11 Prashant Shekhar , Abani Patra

Reproducing kernel Hilbert spaces provide a foundational framework for kernel-based learning, where regularization and interpolation problems admit finite-dimensional solutions through classical representer theorems. Many modern learning…

机器学习 · 计算机科学 2026-02-10 Isabel de la Higuera , Francisco Herrera , M. Victoria Velasco

This study addresses the problem of selecting dynamically, at each time instance, the ``optimal'' p-norm to combat outliers in linear adaptive filtering without any knowledge on the potentially time-varying probability distribution function…

信号处理 · 电气工程与系统科学 2022-10-24 Minh Vu , Yuki Akiyama , Konstantinos Slavakis

Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent -- learning…

机器学习 · 计算机科学 2021-07-21 Denis Yarats , Rob Fergus , Alessandro Lazaric , Lerrel Pinto

In this paper, we present an efficient algorithm for solving a class of chance constrained optimization under non-parametric uncertainty. Our algorithm is built on the possibility of representing arbitrary distributions as functions in…

机器人学 · 计算机科学 2018-11-26 Bharath Gopalakrishnan , Arun Kumar Singh , K. Madhava Krishna , Dinesh Manocha

Unsupervised and self-supervised objectives, such as next token prediction, have enabled pre-training generalist models from large amounts of unlabeled data. In reinforcement learning (RL), however, finding a truly general and scalable…

机器学习 · 计算机科学 2024-05-28 Seohong Park , Tobias Kreiman , Sergey Levine