Stochastic Optimal Control: The Discrete-Time Case
Stochastic Optimal Control: The Discrete-Time Case
New Two-Stage and Sequential Procedures for Selecting the Best Simulated System
Operations Research
Simulation Modeling and Analysis (McGraw-Hill Series in Industrial Engineering and Management)
Simulation Modeling and Analysis (McGraw-Hill Series in Industrial Engineering and Management)
A Knowledge-Gradient Policy for Sequential Information Collection
SIAM Journal on Control and Optimization
The knowledge-gradient stopping rule for ranking and selection
Proceedings of the 40th Conference on Winter Simulation
Selecting a Selection Procedure
Management Science
Economic Analysis of Simulation Selection Problems
Management Science
Continuous-time Stochastic Control and Optimization with Financial Applications
Continuous-time Stochastic Control and Optimization with Financial Applications
Sequential Sampling to Myopically Maximize the Expected Value of Information
INFORMS Journal on Computing
Paradoxes in Learning and the Marginal Value of Information
Decision Analysis
The conjunction of the knowledge gradient and the economic approach to simulation selection
Winter Simulation Conference
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Optimization via simulation with Bayesian statistics and dynamic programming
Proceedings of the Winter Simulation Conference
Sequential screening: a Bayesian dynamic programming analysis of optimal group-splitting
Proceedings of the Winter Simulation Conference
| Hi-index | 0.01 |
Sequential sampling problems arise in stochastic simulation and many other applications. Sampling is used to infer the unknown performance of several alternatives before one alternative is selected as best. This paper presents new economically motivated fully sequential sampling procedures to solve such problems, called economics of selection procedures. The optimal procedure is derived for comparing a known standard with one alternative whose unknown reward is inferred with sampling. That result motivates heuristics when multiple alternatives have unknown rewards. The resulting procedures are more effective in numerical experiments than any previously proposed procedure of which we are aware and are easily implemented. The key driver of the improvement is the use of dynamic programming to model sequential sampling as an option to learn before selecting an alternative. It accounts for the expected benefit of adaptive stopping policies for sampling, rather than of one-stage policies, as is common in the literature. This paper was accepted by Assaf Zeevi, stochastic models and simulation.