Shipra Agrawal

From MaRDI portal
Person:613422

Available identifiers

zbMath Open agrawal.shipraMaRDI QIDQ613422

List of research outcomes





PublicationDate of PublicationType
Optimistic Posterior Sampling for Reinforcement Learning: Worst-Case Regret Bounds2024-02-23Paper
Learning in Structured MDPs with Convex Cost Functions: Improved Regret Bounds for Inventory Management2022-08-05Paper
https://portal.mardi4nfdi.de/entity/Q50903692022-07-18Paper
https://portal.mardi4nfdi.de/entity/Q51490152021-02-05Paper
MNL-Bandit: A Dynamic Learning Approach to Assortment Selection2020-10-26Paper
Bandits with Global Convex Constraints and Objective2020-10-26Paper
Near-Optimal Regret Bounds for Thompson Sampling2018-05-17Paper
Fast Algorithms for Online Stochastic Convex Programming2017-10-05Paper
A Dynamic Near-Optimal Algorithm for Online Linear Programming2014-11-26Paper
https://portal.mardi4nfdi.de/entity/Q54176922014-05-22Paper
Price of correlations in stochastic optimization2012-06-18Paper
Equilibrium in prediction markets with buyers and sellers2010-12-20Paper

Research outcomes over time

This page was built for person: Shipra Agrawal

Retrieved from "https://portal.mardi4nfdi.de/w/index.php?title=Person:613422&oldid=6984785"
Powered by MediaWiki