The ratio index for budgeted learning, with applications

MaRDI QIDQ4633807zbMATH OpenFDO

Authors Ashish Goel, Sanjeev Khanna, Brad Null

Publication date 6 May 2019

Full work available at URL https://dl.acm.org/citation.cfm?id=1496773

Mathematics Subject Classification ID

Stopping times; optimal stopping problems; gambling theory (60G40) Learning and adaptive systems in artificial intelligence (68T05) Approximation algorithms (68W25) Approximation methods and heuristics in mathematical programming (90C59) Rationality and learning in game theory (91A26) Probabilistic games; gambling (91A60)

Recommendations

• Approximation algorithms for budgeted learning problems
• The learning component of dynamic allocation indices
• Optimal learning with non-Gaussian rewards
• On the Gittins index for multiarmed bandits
• Optimistic Gittins Indices

Cited in

(5)

• Matroid prophet inequalities and applications to multi-dimensional mechanism design
• Bayesian Incentive-Compatible Bandit Exploration
• Approximation algorithms for budgeted learning problems
• Two dimensional operator preinvex functions and associated Hermite-Hadamard type inequalities
• The buffered optimization methods for online transfer function identification employed on DEAP actuator

This page was built for publication: The ratio index for budgeted learning, with applications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4633807)