English
Related papers

Related papers: Policy Newton Algorithm in Reproducing Kernel Hilb…

200 papers

Reproducing Kernel Hilbert spaces (RKHS) have been a very successful tool in various areas of machine learning. Recently, Barron spaces have been used to prove bounds on the generalisation error for neural networks. Unfortunately, Barron…

Functional Analysis · Mathematics 2023-03-14 Len Spek , Tjeerd Jan Heeringa , Felix Schwenninger , Christoph Brune

The infinite horizon setting is widely adopted for problems of reinforcement learning (RL). These invariably result in stationary policies that are optimal. In many situations, finite horizon control problems are of interest and for such…

Machine Learning · Computer Science 2025-03-21 Soumyajit Guin , Shalabh Bhatnagar

Off-policy estimation for long-horizon problems is important in many real-life applications such as healthcare and robotics, where high-fidelity simulators may not be available and on-policy evaluation is expensive or impossible. Recently,…

Machine Learning · Computer Science 2020-03-26 Ali Mousavi , Lihong Li , Qiang Liu , Denny Zhou

In the classical Reinforcement Learning from Human Feedback (RLHF) framework, Proximal Policy Optimization (PPO) is employed to learn from sparse, sentence-level rewards -- a challenging scenario in traditional deep reinforcement learning.…

Machine Learning · Computer Science 2025-05-22 Han Zhong , Zikang Shan , Guhao Feng , Wei Xiong , Xinle Cheng , Li Zhao , Di He , Jiang Bian , Liwei Wang

This paper presents strong worst-case iteration and operation complexity guarantees for Riemannian adaptive regularized Newton methods, a unified framework encompassing both Riemannian adaptive regularization (RAR) methods and Riemannian…

Optimization and Control · Mathematics 2025-05-14 Chenyu Zhang , Rujun Jiang

Parametrised quantum circuits offer expressive and data-efficient representations for machine learning. Due to quantum states residing in a high-dimensional Hilbert space, parametrised quantum circuits have a natural interpretation in terms…

Quantum Physics · Physics 2025-08-12 David M. Bossens , Kishor Bharti , Jayne Thompson

A new variant of Newton's method for empirical risk minimization is studied, where at each iteration of the optimization algorithm, the gradient and Hessian of the objective function are replaced by robust estimators taken from existing…

Machine Learning · Statistics 2023-07-18 Eirini Ioannou , Muni Sreenivas Pydi , Po-Ling Loh

A recent goal in the Reinforcement Learning (RL) framework is to choose a sequence of actions or a policy to maximize the reward collected or minimize the regret incurred in a finite time horizon. For several RL problems in operation…

Machine Learning · Computer Science 2016-08-18 K J Prabuchandran , Tejas Bodas , Theja Tulabandhula

We propose a vector-valued regression problem whose solution is equivalent to the reproducing kernel Hilbert space (RKHS) embedding of the Bayesian posterior distribution. This equivalence provides a new understanding of kernel Bayesian…

Machine Learning · Statistics 2016-10-27 Yang Song , Jun Zhu , Yong Ren

We propose a trust region method for policy optimization that employs Quasi-Newton approximation for the Hessian, called Quasi-Newton Trust Region Policy Optimization QNTRPO. Gradient descent is the de facto algorithm for reinforcement…

Machine Learning · Computer Science 2019-12-30 Devesh Jha , Arvind Raghunathan , Diego Romeres

We present novel algorithms for simulation optimization using random directions stochastic approximation (RDSA). These include first-order (gradient) as well as second-order (Newton) schemes. We incorporate both continuous-valued as well as…

Optimization and Control · Mathematics 2015-08-11 Prashanth L. A. , Shalabh Bhatnagar , Michael Fu , Steve Marcus

Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment. In settings with function approximation, many existing RL…

Machine Learning · Computer Science 2026-05-05 Ruiquan Huang , Donghao Li , Yingbin Liang , Jing Yang

Markov decision processes (MDPs) are a well studied framework for solving sequential decision making problems under uncertainty. Exact methods for solving MDPs based on dynamic programming such as policy iteration and value iteration are…

Artificial Intelligence · Computer Science 2015-09-09 Yanping Huang

For a certain scaling of the initialization of stochastic gradient descent (SGD), wide neural networks (NN) have been shown to be well approximated by reproducing kernel Hilbert space (RKHS) methods. Recent empirical work showed that, for…

Machine Learning · Statistics 2022-01-12 Behrooz Ghorbani , Song Mei , Theodor Misiakiewicz , Andrea Montanari

The reliable determination of transition states (TSs) benefits from second-order information for robust convergence and validation, but the computational expense of Hessians prohibits their routine use in TS optimization. Here, we present a…

Chemical Physics · Physics 2026-03-24 Guanchen Wu , Chung-Yueh Yuan , Kareem Hegazy , Samuel M. Blau , Teresa Head-Gordon

We introduce a functional gradient descent trajectory optimization algorithm for robot motion planning in Reproducing Kernel Hilbert Spaces (RKHSs). Functional gradient algorithms are a popular choice for motion planning in complex…

Robotics · Computer Science 2016-01-15 Zita Marinho , Anca Dragan , Arun Byravan , Byron Boots , Siddhartha Srinivasa , Geoffrey Gordon

There are several different notions of "low rank" for tensors, associated to different formats. Among them, the Tensor Train (TT) format is particularly well suited for tensors of high order, as it circumvents the curse of dimensionality:…

Optimization and Control · Mathematics 2020-11-30 Michael Psenka , Nicolas Boumal

In this paper, we consider the nonparametric least square regression in a Reproducing Kernel Hilbert Space (RKHS). We propose a new randomized algorithm that has optimal generalization error bounds with respect to the square loss, closing a…

Machine Learning · Computer Science 2019-05-28 Kwang-Sung Jun , Ashok Cutkosky , Francesco Orabona

In reinforcement learning, we encode the potential behaviors of an agent interacting with an environment into an infinite set of policies, the policy space, typically represented by a family of parametric functions. Dealing with such a…

Machine Learning · Computer Science 2022-02-23 Mirco Mutti , Stefano Del Col , Marcello Restelli

Deep Reinforcement Learning (RL) has shown great success in learning complex control policies for a variety of applications in robotics. However, in most such cases, the hardware of the robot has been considered immutable, modeled as part…

Robotics · Computer Science 2020-11-10 Tianjian Chen , Zhanpeng He , Matei Ciocarlie