English
Related papers

Related papers: A Cubic-regularized Policy Newton Algorithm for Re…

200 papers

Stochastic saddle point (SSP) problems are, in general, less studied compared to stochastic minimization problems. However, SSP problems emerge from machine learning (adversarial training, e.g., GAN, AUC maximization), statistics (robust…

Optimization and Control · Mathematics 2023-12-14 Vitali Pirau

In this paper, we present an online reinforcement learning algorithm for constrained Markov decision processes with a safety constraint. Despite the necessary attention of the scientific community, considering stochastic stopping time, the…

Machine Learning · Computer Science 2024-03-26 Abhijit Mazumdar , Rafal Wisniewski , Manuela L. Bujorianu

We present new large-scale algorithms for fitting a subgradient regularized multivariate convex regression function to $n$ samples in $d$ dimensions -- a key problem in shape constrained nonparametric regression with applications in…

Optimization and Control · Mathematics 2023-12-06 Wenyu Chen , Rahul Mazumder

Reinforcement Learning (RL) has emerged as a powerful framework for sequential decision-making in dynamic environments, particularly when system parameters are unknown. This paper investigates RL-based control for entropy-regularized…

Systems and Control · Electrical Eng. & Systems 2025-12-02 Gabriel Diaz , Lucky Li , Wenhao Zhang

Cubic regularized Newton (CRN) methods have attracted signiffcant research interest because they offer stronger solution guarantees and lower iteration complexity. With the rise of the big-data era, there is growing interest in developing…

Optimization and Control · Mathematics 2025-07-18 Yiming Yang , Chuan He , Xiao Wang , Zheng Peng

Nonconvex optimization problems such as the ones in training deep neural networks suffer from a phenomenon called saddle point proliferation. This means that there are a vast number of high error saddle points present in the loss function.…

Numerical Analysis · Computer Science 2016-11-08 Martin Arjovsky

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

We present a deep reinforcement learning (deep RL) algorithm that consists of learning-based motion planning and imitation to tackle challenging control problems. Deep RL has been an effective tool for solving many high-dimensional…

Robotics · Computer Science 2023-03-02 Nitish Sontakke , Sehoon Ha

Classical reinforcement learning (RL) aims to optimize the expected cumulative rewards. In this work, we consider the RL setting where the goal is to optimize the quantile of the cumulative rewards. We parameterize the policy controlling…

Machine Learning · Computer Science 2022-02-17 Jinyang Jiang , Jiaqiao Hu , Yijie Peng

Since the objective functions of reinforcement learning problems are typically highly nonconvex, it is desirable that policy gradient, the most popular algorithm, escapes saddle points and arrives at second-order stationary points. Existing…

Machine Learning · Computer Science 2024-05-15 Siqiao Mu , Diego Klabjan

This paper addresses the problem of qubit routing in first-generation and other near-term quantum computers. In particular, it is asserted that the qubit routing problem can be formulated as a reinforcement learning (RL) problem, and that…

Quantum Physics · Physics 2019-01-29 Steven Herbert , Akash Sengupta

Reinforcement learning (RL) aims to find an optimal policy by interaction with an environment. Consequently, learning complex behavior requires a vast number of samples, which can be prohibitive in practice. Nevertheless, instead of…

Machine Learning · Computer Science 2021-11-23 Sarah Müller , Alexander von Rohr , Sebastian Trimpe

We explore reinforcement learning methods for finding the optimal policy in the linear quadratic regulator (LQR) problem. In particular, we consider the convergence of policy gradient methods in the setting of known and unknown parameters.…

Machine Learning · Computer Science 2021-06-25 Ben Hambly , Renyuan Xu , Huining Yang

This paper presents a model-free approximation for the Hessian of the performance of deterministic policies to use in the context of Reinforcement Learning based on Quasi-Newton steps in the policy parameters. We show that the approximate…

Machine Learning · Computer Science 2022-03-29 Arash Bahari Kordabad , Hossein Nejatbakhsh Esfahani , Wenqi Cai , Sebastien Gros

Reinforcement Learning (RL) algorithms have shown tremendous success in simulation environments, but their application to real-world problems faces significant challenges, with safety being a major concern. In particular, enforcing…

Machine Learning · Computer Science 2024-06-19 Weiye Zhao , Rui Chen , Yifan Sun , Tianhao Wei , Changliu Liu

We present a random-subspace variant of cubic regularization algorithm that chooses the size of the subspace adaptively, based on the rank of the projected second derivative matrix. Iteratively, our variant only requires access to…

Optimization and Control · Mathematics 2025-01-09 Edward Tansley , Coralia Cartis

Matrix functions are utilized to rewrite smooth spectral constrained matrix optimization problems as smooth unconstrained problems over the set of symmetric matrices which are then solved via the cubic-regularized Newton method. A…

Optimization and Control · Mathematics 2022-09-07 Casey Garner , Gilad Lerman , Shuzhong Zhang

Learning to evaluate and improve policies is a core problem of Reinforcement Learning (RL). Traditional RL algorithms learn a value function defined for a single policy. A recently explored competitive alternative is to learn a single value…

Machine Learning · Computer Science 2022-07-05 Francesco Faccio , Aditya Ramesh , Vincent Herrmann , Jean Harb , Jürgen Schmidhuber

In this work, we develop first-order (Hessian-free) and zero-order (derivative-free) implementations of the Cubically regularized Newton method for solving general non-convex optimization problems. For that, we employ finite difference…

Optimization and Control · Mathematics 2023-09-06 Nikita Doikov , Geovani Nunes Grapiglia

In this theoretical paper we are concerned with the problem of learning a value function by a smooth general function approximator, to solve a deterministic episodic control problem in a large continuous state space. It is shown that…

Machine Learning · Computer Science 2011-01-04 Michael Fairbank , Eduardo Alonso