English
Related papers

Related papers: Accelerated and instance-optimal policy evaluation…

200 papers

We develop and analyze algorithms for instrumental variable regression by viewing the problem as a conditional stochastic optimization problem. In the context of least-squares instrumental variable regression, our algorithms neither require…

Machine Learning · Statistics 2024-05-31 Xuxing Chen , Abhishek Roy , Yifan Hu , Krishnakumar Balasubramanian

We consider emphatic temporal-difference learning algorithms for policy evaluation in discounted Markov decision processes with finite spaces. Such algorithms were recently proposed by Sutton, Mahmood, and White (2015) as an improved…

Machine Learning · Computer Science 2017-12-29 Huizhen Yu

Stochastic constraints, which incorporate both deterministic parameters and random variables, extend classical deterministic constraints by explicitly accounting for uncertainty. These constraints are increasingly prevalent in data science,…

Logic in Computer Science · Computer Science 2026-04-21 Xiakun Li , Hao Wu , Bican Xia , Tengshun Yang , Naijun Zhan

This work studies discrete-time discounted Markov decision processes with continuous state and action spaces and addresses the inverse problem of inferring a cost function from observed optimal behavior. We first consider the case in which…

Optimization and Control · Mathematics 2024-05-27 Angeliki Kamoutsi , Peter Schmitt-Förster , Tobias Sutter , Volkan Cevher , John Lygeros

This paper revisits the temporal difference (TD) learning algorithm for the policy evaluation tasks in reinforcement learning. Typically, the performance of TD(0) and TD($\lambda$) is very sensitive to the choice of stepsizes. Oftentimes,…

Optimization and Control · Mathematics 2021-10-12 Tao Sun , Han Shen , Tianyi Chen , Dongsheng Li

We study the off-policy evaluation (OPE) problem in reinforcement learning with linear function approximation, which aims to estimate the value function of a target policy based on the offline data collected by a behavior policy. We propose…

Machine Learning · Computer Science 2022-01-05 Yifei Min , Tianhao Wang , Dongruo Zhou , Quanquan Gu

In this paper, we investigate the sample complexity of policy evaluation in infinite-horizon offline reinforcement learning (also known as the off-policy evaluation problem) with linear function approximation. We identify a hard regime…

Machine Learning · Computer Science 2021-03-19 Lin Chen , Bruno Scherrer , Peter L. Bartlett

We consider the development of adaptive, instance-dependent algorithms for interactive decision making (bandits, reinforcement learning, and beyond) that, rather than only performing well in the worst case, adapt to favorable properties of…

Machine Learning · Computer Science 2023-04-26 Andrew Wagenmaker , Dylan J. Foster

We study the problem of policy optimization (PO) with linear temporal logic (LTL) constraints. The language of LTL allows flexible description of tasks that may be unnatural to encode as a scalar cost function. We consider LTL-constrained…

Machine Learning · Computer Science 2022-10-21 Cameron Voloshin , Hoang M. Le , Swarat Chaudhuri , Yisong Yue

Reinforcement learning lies at the intersection of several challenges. Many applications of interest involve extremely large state spaces, requiring function approximation to enable tractable computation. In addition, the learner has only a…

Machine Learning · Computer Science 2021-05-11 Andrew Jacobsen , Alan Chan

We initiate a systematic study of utilizing predictions to improve over approximation guarantees of classic algorithms, without increasing the running time. We propose a systematic method for a wide class of optimization problems that ask…

Data Structures and Algorithms · Computer Science 2024-11-26 Antonios Antoniadis , Marek Eliáš , Adam Polak , Moritz Venzin

We study reinforcement learning (RL) with linear function approximation where the underlying transition probability kernel of the Markov decision process (MDP) is a linear mixture model (Jia et al., 2020; Ayoub et al., 2020; Zhou et al.,…

Machine Learning · Computer Science 2021-01-08 Dongruo Zhou , Quanquan Gu , Csaba Szepesvari

We provide faster randomized algorithms for computing an $\epsilon$-optimal policy in a discounted Markov decision process with $A_{\text{tot}}$-state-action pairs, bounded rewards, and discount factor $\gamma$. We provide an…

Machine Learning · Computer Science 2024-05-22 Yujia Jin , Ishani Karmarkar , Aaron Sidford , Jiayi Wang

The key to reconciling the polynomial-time intractability of many machine learning tasks in the worst case with the surprising solvability of these tasks by heuristic algorithms in practice seems to be exploiting restrictions on real-world…

Machine Learning · Computer Science 2022-05-11 Todd Wareham

We investigate the problem of learning an $\epsilon$-approximate solution for the discrete-time Linear Quadratic Regulator (LQR) problem via a Stochastic Variance-Reduced Policy Gradient (SVRPG) approach. Whilst policy gradient methods have…

Optimization and Control · Mathematics 2023-09-20 Leonardo F. Toso , Han Wang , James Anderson

We consider optimization of nonlinear objective functions that balance $d$ linear criteria over $n$-element independence systems presented by linear-optimization oracles. For $d=1$, we have previously shown that an $r$-best approximate…

Optimization and Control · Mathematics 2011-07-05 Jon Lee , Shmuel Onn , Robert Weismantel

We study reinforcement learning (RL) with linear function approximation. For episodic time-inhomogeneous linear Markov decision processes (linear MDPs) whose transition probability can be parameterized as a linear function of a given…

Machine Learning · Computer Science 2023-11-07 Jiafan He , Heyang Zhao , Dongruo Zhou , Quanquan Gu

We propose a novel randomized linear programming algorithm for approximating the optimal policy of the discounted Markov decision problem. By leveraging the value-policy duality and binary-tree data structures, the algorithm adaptively…

Optimization and Control · Mathematics 2019-06-04 Mengdi Wang

Evaluating large language models increasingly relies on LLM-as-a-judge protocols, but such evaluations remain costly: different judges have different prices and reliabilities, and the difficulty of each prompt-response pair can vary…

Machine Learning · Computer Science 2026-05-25 Junghyun Lee , Sanghwa Kim , Yassir Jedra , Alexandre Proutière , Se-Young Yun

Features in machine learning problems are often time-varying and may be related to outputs in an algebraic or dynamical manner. The dynamic nature of these machine learning problems renders current higher order accelerated gradient descent…

Optimization and Control · Mathematics 2019-05-29 Joseph E. Gaudio , Travis E. Gibson , Anuradha M. Annaswamy , Michael A. Bolender