Finite-Time Analysis for the Knowledge-Gradient Policy (Q4610155): Difference between revisions

@@ Property / describes a project that uses @@
+BayesDA
@@ Property / describes a project that uses: BayesDA / rank @@
+Normal rank
@@ Property / MaRDI profile type @@
+MaRDI publication profile
@@ Property / MaRDI profile type: MaRDI publication profile / rank @@
+Normal rank
@@ Property / arXiv ID @@
+.04624
@@ Property / arXiv ID: 1606.04624 / rank @@
+Normal rank
@@ Property / cites work @@
+Sample mean based index policies by <i>O</i>(log <i>n</i>) regret for the multi-armed bandit problem
+Normal rank
@@ Property / cites work @@
+Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
+Normal rank
@@ Property / cites work @@
+Finite-time analysis of the multiarmed bandit problem
+Normal rank
@@ Property / cites work @@
+Optimal learning for sequential sampling with non-parametric beliefs
+Normal rank
@@ Property / cites work @@
+Selecting a Selection Procedure
@@ Property / cites work: Selecting a Selection Procedure / rank @@
+Normal rank
@@ Property / cites work @@
+Bandits With Heavy Tail
@@ Property / cites work: Bandits With Heavy Tail / rank @@
+Normal rank
@@ Property / cites work @@
+Kullback-Leibler upper confidence bounds for optimal sequential allocation
+Normal rank
@@ Property / cites work @@
+Efficient Dynamic Simulation Allocation in Ordinal Optimization
+Normal rank
@@ Property / cites work @@
+Simulation budget allocation for further enhancing the efficiency of ordinal optimization
+Normal rank
@@ Property / cites work @@
+The Knowledge-Gradient Policy for Correlated Normal Beliefs
+Normal rank
@@ Property / cites work @@
+A Knowledge-Gradient Policy for Sequential Information Collection
+Normal rank
@@ Property / cites work @@
+On Upper-Confidence Bound Policies for Switching Bandit Problems
+Normal rank
@@ Property / cites work @@
+Q2873072
@@ Property / cites work: Q2873072 / rank @@
+Normal rank
@@ Property / cites work @@
+Q4197923
@@ Property / cites work: Q4197923 / rank @@
+Normal rank
@@ Property / cites work @@
+The Data-Correcting Algorithm for the Minimization of Supermodular Functions
+Normal rank
@@ Property / cites work @@
+Q5689624
@@ Property / cites work: Q5689624 / rank @@
+Normal rank
@@ Property / cites work @@
+Bayesian look ahead one-stage sampling allocations for selection of the best population
+Normal rank
@@ Property / cites work @@
+A Bayesian Approach to Some Best Population Problems
+Normal rank
@@ Property / cites work @@
+Global optimization of stochastic black-box systems via sequential kriging meta-models
+Normal rank
@@ Property / cites work @@
+Efficient global optimization of expensive black-box functions
+Normal rank
@@ Property / cites work @@
+Regret bounds for sleeping experts and bandits
@@ Property / cites work: Regret bounds for sleeping experts and bandits / rank @@
+Normal rank
@@ Property / cites work @@
+Asymptotically efficient adaptive allocation rules
+Normal rank
@@ Property / cites work @@
+Q5396715
@@ Property / cites work: Q5396715 / rank @@
+Normal rank
@@ Property / cites work @@
+Q3993195
@@ Property / cites work: Q3993195 / rank @@
+Normal rank
@@ Property / cites work @@
+The Knowledge-Gradient Algorithm for Sequencing Experiments in Drug Discovery
+Normal rank
@@ Property / cites work @@
+An analysis of approximations for maximizing submodular set functions—I
+Normal rank
@@ Property / cites work @@
+Q4497726
@@ Property / cites work: Q4497726 / rank @@
+Normal rank
@@ Property / cites work @@
+Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
+Normal rank
@@ Property / OpenAlex ID @@
+W2963389017
@@ Property / OpenAlex ID: W2963389017 / rank @@
+Normal rank
@@ Property / Wikidata QID @@
+Q130050586
@@ Property / Wikidata QID: Q130050586 / rank @@
+Normal rank