English
Related papers

Related papers: Policy Mirror Descent for Reinforcement Learning: …

200 papers

In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the…

Machine Learning · Computer Science 2021-01-29 Sobhan Miryoosefi , Kianté Brantley , Hal Daumé , Miroslav Dudik , Robert Schapire

Recent work by Woodworth et al. (2020) shows that the optimization dynamics of gradient descent for overparameterized problems can be viewed as low-dimensional dual dynamics induced by a mirror map, explaining the implicit regularization…

Machine Learning · Computer Science 2024-10-21 Shuyang Wang , Diego Klabjan

Reinforcement Learning (RL) has made significant strides in complex tasks but struggles in multi-task settings with different embodiments. World model methods offer scalability by learning a simulation of the environment but often rely on…

Machine Learning · Computer Science 2025-02-25 Ignat Georgiev , Varun Giridhar , Nicklas Hansen , Animesh Garg

This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consist of iteratively adjusting the reward function to transform…

Optimization and Control · Mathematics 2026-04-23 Simone Baroncini , Bahman Gharesifard , Giuseppe Notarstefano

Low-rank modeling has a lot of important applications in machine learning, computer vision and social network analysis. While the matrix rank is often approximated by the convex nuclear norm, the use of nonconvex low-rank regularizers has…

Numerical Analysis · Computer Science 2016-05-02 Quanming Yao , James T. Kwok , Wenliang Zhong

We consider the constrained sampling problem where the goal is to sample from a target distribution $\pi(x)\propto e^{-f(x)}$ when $x$ is constrained to lie on a convex body $\mathcal{C}$. Motivated by penalty methods from continuous…

Machine Learning · Statistics 2025-05-16 Mert Gürbüzbalaban , Yuanhan Hu , Lingjiong Zhu

We present a reduction from reinforcement learning (RL) to no-regret online learning based on the saddle-point formulation of RL, by which "any" online algorithm with sublinear regret can generate policies with provable performance…

Machine Learning · Computer Science 2020-01-03 Ching-An Cheng , Remi Tachet des Combes , Byron Boots , Geoff Gordon

Low-rank modeling has many important applications in computer vision and machine learning. While the matrix rank is often approximated by the convex nuclear norm, the use of nonconvex low-rank regularizers has demonstrated better empirical…

Machine Learning · Computer Science 2018-07-25 Quanming Yao , James T. Kwok , Taifeng Wang , Tie-Yan Liu

As the problem of minimizing functionals on the Wasserstein space encompasses many applications in machine learning, different optimization algorithms on $\mathbb{R}^d$ have received their counterpart analog on the Wasserstein space. We…

Optimization and Control · Mathematics 2024-11-20 Clément Bonet , Théo Uscidda , Adam David , Pierre-Cyril Aubin-Frankowski , Anna Korba

In this paper, we propose and analyse a family of generalised stochastic composite mirror descent algorithms. With adaptive step sizes, the proposed algorithms converge without requiring prior knowledge of the problem. Combined with an…

Optimization and Control · Mathematics 2022-11-22 Weijia Shao , Fikret Sivrikaya , Sahin Albayrak

In this paper, we investigate the power of {\it regularization}, a common technique in reinforcement learning and optimization, in solving extensive-form games (EFGs). We propose a series of new algorithms based on regularizing the payoff…

Computer Science and Game Theory · Computer Science 2025-07-10 Mingyang Liu , Asuman Ozdaglar , Tiancheng Yu , Kaiqing Zhang

Owing to their connection with generative adversarial networks (GANs), saddle-point problems have recently attracted considerable interest in machine learning and beyond. By necessity, most theoretical guarantees revolve around…

Recent years have seen a flurry of activities in designing provably efficient nonconvex procedures for solving statistical estimation problems. Due to the highly nonconvex nature of the empirical loss, state-of-the-art procedures often…

Machine Learning · Computer Science 2020-06-09 Cong Ma , Kaizheng Wang , Yuejie Chi , Yuxin Chen

Reinforcement Learning (RL) encompasses diverse paradigms, including model-based RL, policy-based RL, and value-based RL, each tailored to approximate the model, optimal policy, and optimal value function, respectively. This work…

Machine Learning · Computer Science 2024-12-10 Guhao Feng , Han Zhong

We study the setting of \emph{performative reinforcement learning} where the deployed policy affects both the reward, and the transition of the underlying Markov decision process. Prior work~\parencite{MTR23} has addressed this problem…

Machine Learning · Computer Science 2025-03-18 Debmalya Mandal , Goran Radanovic

Policy gradient (PG) gives rise to a rich class of reinforcement learning (RL) methods. Recently, there has been an emerging trend to accelerate the existing PG methods such as REINFORCE by the \emph{variance reduction} techniques. However,…

Machine Learning · Computer Science 2021-05-31 Junyu Zhang , Chengzhuo Ni , Zheng Yu , Csaba Szepesvari , Mengdi Wang

Consider linear ill-posed problems governed by the system $A_i x = y_i$ for $i =1, \cdots, p$, where each $A_i$ is a bounded linear operator from a Banach space $X$ to a Hilbert space $Y_i$. In case $p$ is huge, solving the problem by an…

Numerical Analysis · Mathematics 2023-05-17 Qinian Jin , Xiliang Lu , Liuying Zhang

In this paper, we investigate the non-asymptotic stationary convergence behavior of Stochastic Mirror Descent (SMD) for nonconvex optimization. We focus on a general class of nonconvex nonsmooth stochastic optimization problems, in which…

Optimization and Control · Mathematics 2018-06-14 Siqi Zhang , Niao He

Many problems in machine learning can be formulated as optimizing a convex functional over a vector space of measures. This paper studies the convergence of the mirror descent algorithm in this infinite-dimensional setting. Defining Bregman…

Optimization and Control · Mathematics 2022-10-12 Pierre-Cyril Aubin-Frankowski , Anna Korba , Flavien Léger

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by…

Machine Learning · Statistics 2020-08-28 Tomas Vaškevičius , Varun Kanade , Patrick Rebeschini
‹ Prev 1 4 5 6 7 8 10 Next ›