Pages that link to "Item:Q3648740"

The following pages link to Pure Exploration in Multi-armed Bandits Problems (Q3648740):

Displaying 19 items.

• Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization (Q72746) (← links)
• Algorithm portfolios for noisy optimization (Q276539) (← links)
• Modification of improved upper confidence bounds for regulating exploration in Monte-Carlo tree search (Q307787) (← links)
• Multi-armed bandits with episode context (Q766259) (← links)
• Adaptive-treed bandits (Q888482) (← links)
• Efficient crowdsourcing of unknown experts using bounded multi-armed bandits (Q2014933) (← links)
• Sequential estimation of quantiles with applications to A/B testing and best-arm identification (Q2137037) (← links)
• Pure Exploration in Multi-armed Bandits Problems (Q3648740) (← links)
• (Q4558161) (← links)
• A Bandit-Learning Approach to Multifidelity Approximation (Q5022495) (← links)
• Optimal Policy for Dynamic Assortment Planning Under Multinomial Logit Models (Q5026455) (← links)
• Smoothness-Adaptive Contextual Bandits (Q5060496) (← links)
• Always Valid Inference: Continuous Monitoring of A/B Tests (Q5095177) (← links)
• Tractable Sampling Strategies for Ordinal Optimization (Q5131546) (← links)
• Simple Bayesian Algorithms for Best-Arm Identification (Q5144786) (← links)
• Convergence rate analysis for optimal computing budget allocation algorithms (Q6110297) (← links)
• Constrained regret minimization for multi-criterion multi-armed bandits (Q6155194) (← links)
• Treatment recommendation with distributional targets (Q6163253) (← links)
• Finding the optimal exploration-exploitation trade-off online through Bayesian risk estimation and minimization (Q6566614) (← links)