English
Related papers

Related papers: How Log-Barrier Helps Exploration in Policy Optimi…

200 papers

We consider a stochastic multi-armed bandit setting and study the problem of constrained regret minimization over a given time horizon. Each arm is associated with an unknown, possibly multi-dimensional distribution, and the merit of an arm…

Machine Learning · Computer Science 2023-01-05 Anmol Kagrecha , Jayakrishnan Nair , Krishna Jagannathan

In stochastic contextual bandit (SCB) problems, an agent selects an action based on certain observed context to maximize the cumulative reward over iterations. Recently there have been a few studies using a deep neural network (DNN) to…

Machine Learning · Computer Science 2021-04-23 Tan Zhu , Guannan Liang , Chunjiang Zhu , Haining Li , Jinbo Bi

Constrained Reinforcement Learning (CRL) addresses sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints. In this setting, policy-based…

Machine Learning · Computer Science 2025-06-09 Alessandro Montenegro , Leonardo Cesani , Marco Mussi , Matteo Papini , Alberto Maria Metelli

In this paper, we introduce the notion of replicable policies in the context of stochastic bandits, one of the canonical problems in interactive learning. A policy in the bandit environment is called replicable if it pulls, with high…

Machine Learning · Computer Science 2023-02-16 Hossein Esfandiari , Alkis Kalavasis , Amin Karbasi , Andreas Krause , Vahab Mirrokni , Grigoris Velegkas

We study the Stochastic Gradient Langevin Dynamics (SGLD) algorithm for non-convex optimization. The algorithm performs stochastic gradient descent, where in each step it injects appropriately scaled Gaussian noise to the update. We analyze…

Machine Learning · Computer Science 2018-04-10 Yuchen Zhang , Percy Liang , Moses Charikar

In this paper, we consider a general stochastic optimization problem which is often at the core of supervised learning, such as deep learning and linear classification. We consider a standard stochastic gradient descent (SGD) method with a…

Machine Learning · Statistics 2018-12-27 Lam M. Nguyen , Nam H. Nguyen , Dzung T. Phan , Jayant R. Kalagnanam , Katya Scheinberg

Modifying the reward-biased maximum likelihood method originally proposed in the adaptive control literature, we propose novel learning algorithms to handle the explore-exploit trade-off in linear bandits problems as well as generalized…

Machine Learning · Computer Science 2020-10-09 Yu-Heng Hung , Ping-Chun Hsieh , Xi Liu , P. R. Kumar

We study the sample complexity of learning an $\epsilon$-optimal policy in the Stochastic Shortest Path (SSP) problem. We first derive sample complexity bounds when the learner has access to a generative model. We show that there exists a…

Machine Learning · Computer Science 2022-10-12 Liyu Chen , Andrea Tirinzoni , Matteo Pirotta , Alessandro Lazaric

Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former…

Machine Learning · Computer Science 2021-01-07 Branislav Kveton , Martin Mladenov , Chih-Wei Hsu , Manzil Zaheer , Csaba Szepesvari , Craig Boutilier

We study the problem of estimating the expected reward of the optimal policy in the stochastic disjoint linear bandit setting. We prove that for certain settings it is possible to obtain an accurate estimate of the optimal policy value even…

Machine Learning · Computer Science 2019-12-17 Weihao Kong , Gregory Valiant , Emma Brunskill

We consider discounted infinite-horizon constrained Markov decision processes (CMDPs), where the goal is to find an optimal policy that maximizes the expected cumulative reward while satisfying expected cumulative constraints. Motivated by…

Machine Learning · Computer Science 2025-03-04 Tingting Ni , Maryam Kamgarpour

We introduce a general framework for analyzing learning algorithms based on the notion of self-regularization, which captures implicit complexity control without requiring explicit regularization. This is motivated by previous observations…

Machine Learning · Statistics 2026-03-19 Max Schölpple , Liu Fanghui , Ingo Steinwart

Batch policy optimization considers leveraging existing data for policy construction before interacting with an environment. Although interest in this problem has grown significantly in recent years, its theoretical foundations remain…

Machine Learning · Computer Science 2021-04-07 Chenjun Xiao , Yifan Wu , Tor Lattimore , Bo Dai , Jincheng Mei , Lihong Li , Csaba Szepesvari , Dale Schuurmans

In this paper, we revisit and improve the convergence of policy gradient (PG), natural PG (NPG) methods, and their variance-reduced variants, under general smooth policy parametrizations. More specifically, with the Fisher information…

Machine Learning · Computer Science 2022-11-17 Yanli Liu , Kaiqing Zhang , Tamer Başar , Wotao Yin

The difficulty in specifying rewards for many real-world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are often many different reward functions that explain the human…

Machine Learning · Computer Science 2021-06-23 Zaynah Javed , Daniel S. Brown , Satvik Sharma , Jerry Zhu , Ashwin Balakrishna , Marek Petrik , Anca D. Dragan , Ken Goldberg

Domain randomization is a simple, effective, and flexible scheme for obtaining robust feedback policies aimed at reducing the sim-to-real gap due to model mismatch. While domain randomization methods have yielded impressive demonstrations…

Systems and Control · Electrical Eng. & Systems 2026-03-17 Alex Nguyen-Le , Nikolai Matni

We prove that, for finite-arm bandits with linear function approximation, the global convergence of policy gradient (PG) methods depends on inter-related properties between the policy update and the representation. textcolor{blue}{First},…

Machine Learning · Computer Science 2025-04-04 Jincheng Mei , Bo Dai , Alekh Agarwal , Mohammad Ghavamzadeh , Csaba Szepesvari , Dale Schuurmans

We study to what extent may stochastic gradient descent (SGD) be understood as a "conventional" learning rule that achieves generalization performance by obtaining a good fit to training data. We consider the fundamental stochastic convex…

Machine Learning · Computer Science 2023-01-13 Tomer Koren , Roi Livni , Yishay Mansour , Uri Sherman

Stochastic variance-reduced gradient (SVRG) is an optimization method originally designed for tackling machine learning problems with a finite sum structure. SVRG was later shown to work for policy evaluation, a problem in reinforcement…

Machine Learning · Computer Science 2020-06-22 Zilun Peng , Ahmed Touati , Pascal Vincent , Doina Precup

Variance reduction has been commonly used in stochastic optimization. It relies crucially on the assumption that the data set is finite. However, when the data are imputed with random noise as in data augmentation, the perturbed data set…

Machine Learning · Computer Science 2018-06-11 Shuai Zheng , James T. Kwok