Add to ORKGIncludes bibliographical references (p. 19-21).Supported by a Presidential Young Investigator Award. 9158118 Supported by matching funds from Draper Laboratory and a Ministry of Education & Science of Spain Doctoral Fellowship.Dimitris Bertsimas, José Niño-Mora
We show that if performance measures in stochastic and dynamic scheduling problems satisfy generaliz...
155 pagesWe consider multi-action restless bandits with multiple resource constraints, also referred...
Combinatorial stochastic semi-bandits appear naturally in many contexts where the exploration/exploi...
We propose a mathematical programming approach for the classical PSPACE - hard problem of n restless...
Abstract—The multi-armed bandit problem and one of its most interesting extensions, the restless ban...
Includes bibliographical references (p. 46-50).Supported by a Presidential Young Investigator Award....
Thesis (Ph. D.)--Massachusetts Institute of Technology, Sloan School of Management, Operations Resea...
Cover title.Includes bibliographical references (p. 44-48).Supported in part by a Presidential Young...
Dynamic programming is a principal method for analyzing stochastic optimal control problems. However...
This paper develops a framework based on convex optimization and economic ideas to formulate and sol...
We provide a framework to analyse control policies for the restless Markovian bandit model, under bo...
Includes bibliographical references (p. 22-24).Supported by a Presidential Young Investigator Award....
We consider the information relaxation approach for calculating performance bounds for stochastic dy...
In this thesis we study constraint relaxations of various nonlinear programming (NLP) al-gorithms in...
We study the min max optimization problem introduced in Fonteneau et al. [Towards min max reinforcem...
We show that if performance measures in stochastic and dynamic scheduling problems satisfy generaliz...
155 pagesWe consider multi-action restless bandits with multiple resource constraints, also referred...
Combinatorial stochastic semi-bandits appear naturally in many contexts where the exploration/exploi...
We propose a mathematical programming approach for the classical PSPACE - hard problem of n restless...
Abstract—The multi-armed bandit problem and one of its most interesting extensions, the restless ban...
Includes bibliographical references (p. 46-50).Supported by a Presidential Young Investigator Award....
Thesis (Ph. D.)--Massachusetts Institute of Technology, Sloan School of Management, Operations Resea...
Cover title.Includes bibliographical references (p. 44-48).Supported in part by a Presidential Young...
Dynamic programming is a principal method for analyzing stochastic optimal control problems. However...
This paper develops a framework based on convex optimization and economic ideas to formulate and sol...
We provide a framework to analyse control policies for the restless Markovian bandit model, under bo...
Includes bibliographical references (p. 22-24).Supported by a Presidential Young Investigator Award....
We consider the information relaxation approach for calculating performance bounds for stochastic dy...
In this thesis we study constraint relaxations of various nonlinear programming (NLP) al-gorithms in...
We study the min max optimization problem introduced in Fonteneau et al. [Towards min max reinforcem...
We show that if performance measures in stochastic and dynamic scheduling problems satisfy generaliz...
155 pagesWe consider multi-action restless bandits with multiple resource constraints, also referred...
Combinatorial stochastic semi-bandits appear naturally in many contexts where the exploration/exploi...