English
Related papers

Related papers: Getting to "rate-optimal'' in ranking & selection

200 papers

Experience replay \citep{lin1993reinforcement, mnih2015human} is a widely used technique to achieve efficient use of data and improved performance in RL algorithms. In experience replay, past transitions are stored in a memory buffer and…

Machine Learning · Computer Science 2021-12-09 Liran Szlak , Ohad Shamir

Consider a multi-agent system in a dynamic and uncertain environment. Each agent's local decision problem is modeled as a Markov decision process (MDP) and agents must coordinate on a joint action in each period, which provides a reward to…

Computer Science and Game Theory · Computer Science 2012-07-02 Ruggiero Cavallo , David C. Parkes , Satinder Singh

Fair division is a fundamental problem in various multi-agent settings, where the goal is to divide a set of resources among agents in a fair manner. We study the case where m indivisible items need to be divided among n agents with…

Computer Science and Game Theory · Computer Science 2021-04-07 Jugal Garg , Setareh Taki

We introduce a novel class of algorithms to efficiently approximate the unknown return distributions in policy evaluation problems from distributional reinforcement learning (DRL). The proposed distributional dynamic programming algorithms…

Machine Learning · Statistics 2024-07-22 Julian Gerstenberg , Ralph Neininger , Denis Spiegel

Regression testing is key in verifying that software works correctly after changes. However, running the entire regression test suite can be impractical and expensive, especially for large-scale systems. Test suite optimization methods are…

Quantum Physics · Physics 2025-05-01 Antonio Trovato , Martin Beseda , Dario Di Nucci

This paper investigates to what extent one can improve reinforcement learning algorithms. Our study is split in three parts. First, our analysis shows that the classical asymptotic convergence rate $O(1/\sqrt{N})$ is pessimistic and can be…

Machine Learning · Computer Science 2021-10-25 Othmane Mounjid , Charles-Albert Lehalle

In this paper, a stochastic approximation (SA) based distributed algorithm is proposed to solve the resource allocation (RA) with uncertainties. In this problem, a group of agents cooperatively optimize a separable optimization problem with…

Optimization and Control · Mathematics 2016-11-01 Peng Yi , Jinlong Lei , Yiguang Hong

We study the limits of bipartite entanglement distribution using a chain of quantum repeaters that have quantum memories. To generate end-to-end entanglement, each node can attempt the generation of an entangled link with a neighbor, or…

Quantum Physics · Physics 2023-05-11 Álvaro G. Iñesta , Gayane Vardoyan , Lara Scavuzzo , Stephanie Wehner

Q-learning is a popular Reinforcement Learning (RL) algorithm which is widely used in practice with function approximation (Mnih et al., 2015). In contrast, existing theoretical results are pessimistic about Q-learning. For example, (Baird,…

Machine Learning · Computer Science 2021-10-20 Naman Agarwal , Syomantak Chaudhuri , Prateek Jain , Dheeraj Nagaraj , Praneeth Netrapalli

Reinforcement Learning algorithms are primarily focused on learning a policy that maximizes expected return. As a result, the learned policy can exploit one or few reward sources. However, in many natural situations, it is desirable to…

Machine Learning · Computer Science 2026-03-31 Sagalpreet Singh , Rishi Saket , Aravindan Raghuveer

We want to recover the regression function in the single-index model. Using an aggregation algorithm with local polynomial estimators, we answer in particular to the second part of Question~2 from Stone (1982) on the optimal convergence…

Statistics Theory · Mathematics 2007-12-04 Stéphane Gaïffas , Guillaume Lecué

Ranking and selection (R&S) aims to select the best alternative with the largest mean performance from a finite set of alternatives. Recently, considerable attention has turned towards the large-scale R&S problem which involves a large…

Methodology · Statistics 2025-09-09 Zaile Li , Weiwei Fan , L. Jeff Hong

We compare the outcomes of the most prominent strategy-proof and stable algorithm (Deferred Acceptance, DA) and the most prominent strategy-proof and Pareto optimal algorithm (Top Trading Cycles, TTC) to the allocation generated by the…

Theoretical Economics · Economics 2023-07-28 Josue Ortega , Thilo Klein

We study a ranking and selection (R&S) problem when all solutions share common parametric Bayesian input models updated with the data collected from multiple independent data-generating sources. Our objective is to identify the best system…

Methodology · Statistics 2025-02-25 Eunhye Song , Taeho Kim

This brief paper presents simple simulation-based algorithms for obtaining an approximately optimal policy in a given finite set in large finite constrained Markov decision processes. The algorithms are adapted from playing strategies for…

Optimization and Control · Mathematics 2014-12-17 Hyeong Soo Chang

The theory of reinforcement learning has focused on two fundamental problems: achieving low regret, and identifying $\epsilon$-optimal policies. While a simple reduction allows one to apply a low-regret algorithm to obtain an…

Machine Learning · Computer Science 2022-06-23 Andrew Wagenmaker , Max Simchowitz , Kevin Jamieson

Recently, $\alpha$-Rank, a graph-based algorithm, has been proposed as a solution to ranking joint policy profiles in large scale multi-agent systems. $\alpha$-Rank claimed tractability through a polynomial time implementation with respect…

Multiagent Systems · Computer Science 2020-03-04 Yaodong Yang , Rasul Tutunov , Phu Sakulwongtana , Haitham Bou Ammar

Policy iteration enjoys a local quadratic rate of contraction, but its iterations are computationally expensive for Markov decision processes (MDPs) with a large number of states. In light of the connection between policy iteration and the…

Optimization and Control · Mathematics 2022-11-09 Matilde Gargiani , Dominic Liao-McPherson , Andrea Zanelli , John Lygeros

Each year, thousands of patients in need of heart transplants face life-threatening wait times due to organ scarcity. While allocation policies aim to maximize population-level outcomes, current approaches often fail to account for the…

Machine Learning · Computer Science 2026-02-10 Itai Zilberstein , Ioannis Anagnostides , Zachary W. Sollie , Arman Kilic , Tuomas Sandholm

Maximal Independent Set selection is a fundamental problem in distributed computing. A novel probabilistic algorithm for this problem has recently been proposed by Afek et al, inspired by the study of the way that developing cells in the…

Distributed, Parallel, and Cluster Computing · Computer Science 2012-11-02 Alex Scott , Peter Jeavons , Lei Xu