scientific article

From MaRDI portal
Publication:3046711

zbMath1050.68059MaRDI QIDQ3046711

Shie Mannor, Yishay Mansour, Eyal Even-Dar

Publication date: 12 August 2004

Full work available at URL: http://link.springer.de/link/service/series/0558/bibs/2375/23750255.htm

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.



Related Items (21)

Best Arm Identification for Contaminated BanditsApproximation algorithms for stochastic combinatorial optimization problemsSequential estimation of quantiles with applications to A/B testing and best-arm identificationSolving Large-Scale Fixed-Budget Ranking and Selection ProblemsAlways Valid Inference: Continuous Monitoring of A/B TestsUnnamed ItemAn asymptotically optimal policy for finite support models in the multiarmed bandit problemPure exploration in finitely-armed and continuous-armed banditsAmplification and Derandomization without SlowdownTractable Sampling Strategies for Ordinal OptimizationSimple Bayesian Algorithms for Best-Arm IdentificationEfficient PAC learning for episodic tasks with acyclic state spacesAn analysis of model-based interval estimation for Markov decision processesAdaptive Incentive-Compatible Sponsored Search AuctionPreference-based reinforcement learning: evolutionary direct policy search using a preference-based racing algorithmPolynomial-Time Algorithms for Multiple-Arm Identification with Full-Bandit FeedbackBayesian Incentive-Compatible Bandit ExplorationPure Exploration in Multi-armed Bandits ProblemsA PAC algorithm in relative precision for bandit problem with costly samplingTrading utility and uncertainty: applying the value of information to resolve the exploration-exploitation dilemma in reinforcement learningKnockout-Tournament Procedures for Large-Scale Ranking and Selection in Parallel Computing Environments


Uses Software



This page was built for publication: