English
Related papers

Related papers: Accelerated Reinforcement Learning

200 papers

Recently, {\it stochastic momentum} methods have been widely adopted in training deep neural networks. However, their convergence analysis is still underexplored at the moment, in particular for non-convex optimization. This paper fills the…

Optimization and Control · Mathematics 2016-05-06 Tianbao Yang , Qihang Lin , Zhe Li

We consider gradient descent with `momentum', a widely used method for loss function minimization in machine learning. This method is often used with `Nesterov acceleration', meaning that the gradient is evaluated not at the current…

Machine Learning · Computer Science 2020-01-20 Goran Nakerst , John Brennan , Masudul Haque

Since its introduction a decade ago, \emph{relative entropy policy search} (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains, not to mention providing algorithmic components used by…

Machine Learning · Computer Science 2021-03-18 Aldo Pacchiano , Jonathan Lee , Peter Bartlett , Ofir Nachum

The optimized gradient method (OGM) provides a factor-$\sqrt{2}$ speedup upon Nesterov's celebrated accelerated gradient method in the convex (but non-strongly convex) setup. However, this improved acceleration mechanism has not been well…

Optimization and Control · Mathematics 2021-05-25 Chanwoo Park , Jisun Park , Ernest K. Ryu

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which…

Machine Learning · Computer Science 2026-05-01 Mohammad Ghavamzadeh , Yaakov Engel , Michal Valko

In this work, based on the continuous time approach, we propose an accelerated gradient method with adaptive residual restart for convex multiobjective optimization problems. For the first, we derive rigorously the continuous limit of the…

Optimization and Control · Mathematics 2025-02-06 Hao Luo , Liping Tang , Xinmin Yang

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong…

Machine Learning · Computer Science 2020-10-23 Jorge A. Mendez , Boyu Wang , Eric Eaton

We propose a new method for unconstrained optimization of a smooth and strongly convex function, which attains the optimal rate of convergence of Nesterov's accelerated gradient descent. The new algorithm has a simple geometric…

Optimization and Control · Mathematics 2015-06-30 Sébastien Bubeck , Yin Tat Lee , Mohit Singh

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

We prove under commonly used assumptions the convergence of actor-critic reinforcement learning algorithms, which simultaneously learn a policy function, the actor, and a value function, the critic. Both functions can be deep neural…

Machine Learning · Computer Science 2020-12-03 Markus Holzleitner , Lukas Gruber , José Arjona-Medina , Johannes Brandstetter , Sepp Hochreiter

A novel dynamical inertial Newton system, which is called Hessian-driven Nesterov accelerated gradient (H-NAG) flow is proposed. Convergence of the continuous trajectory are established via tailored Lyapunov function, and new first-order…

Optimization and Control · Mathematics 2019-12-25 Long Chen , Hao Luo

This paper considers policy search in continuous state-action reinforcement learning problems. Typically, one computes search directions using a classic expression for the policy gradient called the Policy Gradient Theorem, which decomposes…

Machine Learning · Computer Science 2020-04-13 Sujay Bhatt , Alec Koppel , Vikram Krishnamurthy

To learn approximately optimal acting policies for decision problems, modern Actor Critic algorithms rely on deep Neural Networks (DNNs) to parameterize the acting policy and greedification operators to iteratively improve it. The reliance…

Accelerated gradient methods play a central role in optimization, achieving optimal rates in many settings. While many generalizations and extensions of Nesterov's original acceleration method have been proposed, it is not yet clear what is…

Optimization and Control · Mathematics 2022-06-08 Andre Wibisono , Ashia C. Wilson , Michael I. Jordan

Motivated by the success of Nesterov's accelerated gradient algorithm for convex minimization problems, we examine whether it is possible to achieve similar performance gains in the context of online learning in games. To that end, we…

Computer Science and Game Theory · Computer Science 2024-12-31 Kyriakos Lotidis , Angeliki Giannou , Panayotis Mertikopoulos , Nicholas Bambos

Policy gradient (PG) methods are a class of effective reinforcement learning algorithms, particularly when dealing with continuous control problems. They rely on fresh on-policy data, making them sample-inefficient and requiring…

Machine Learning · Computer Science 2026-02-03 Alessandro Montenegro , Federico Mansutti , Marco Mussi , Matteo Papini , Alberto Maria Metelli

We study accelerated optimization methods in the Gaussian phase retrieval problem. In this setting, we prove that gradient methods with Polyak or Nesterov momentum have similar implicit regularization to gradient descent. This implicit…

Optimization and Control · Mathematics 2023-11-23 Tyler Maunu , Martin Molina-Fructuoso

Despite the success achieved by the analysis of supervised learning algorithms in the framework of statistical mechanics, reinforcement learning has remained largely untouched. Here we move towards closing the gap by analyzing the dynamics…

Statistical Mechanics · Physics 2022-09-02 Riccardo Fabbricatore , Vladimir V. Palyulin

We present a unified convergence analysis for first order convex optimization methods using the concept of strong Lyapunov conditions. Combining this with suitable time scaling factors, we are able to handle both convex and strong convex…

Optimization and Control · Mathematics 2021-08-03 Long Chen , Hao Luo

We provide a novel accelerated first-order method that achieves the asymptotically optimal convergence rate for smooth functions in the first-order oracle model. To this day, Nesterov's Accelerated Gradient Descent (AGD) and variations…

Optimization and Control · Mathematics 2018-02-13 Jelena Diakonikolas , Lorenzo Orecchia