Randomization in the two-armed bandit problem
This paper gives an elementary proof of the existence of optimal solutions to a general form of the continuous-time two-armed bandit. The formulation is the same as that used by \textit{G. Mazziotto} and \textit{A. Millet} [Stochastics 22, 251-288 (1987; Zbl 0643.60040)]; however the topological embedding of the set of randomized optimal increasing paths is new and enables a resolution of the problem that requires only straightforward topological arguments. Also, one of the conditions in Mazziotto and Millet's paper can be removed, yielding a stronger result.
- The two-armed bandit problem with continuous time in the presence of gradual and impulsive controls
- A Two-Armed Bandit Problem with possibility of no Information
- Further contributions to the two-armed bandit problem
- Stochastic control of two-parameter processes application:the two-armed bandit problem
- On the Optimal Reward Function of the Continuous Time Multiarmed Bandit Problem
- Further contributions to the two-armed bandit problem
- The set-indexed bandit problem.
- Sensitivity of the gittins index in the contiuous time two-armed bandit problem
- A two armed bandit type problem revisited
- The two-armed bandit problem with continuous time in the presence of gradual and impulsive controls
- scientific article; zbMATH DE number 3911530 (Why is no real title available?)
- On ergodic two-armed bandits
- Some results on two-armed bandits when both projects vary
- Baxter-Chacon topology and optimality for multivariate stopping of two-parameter stochastic processes
- An exact bandit model for the risk-volatility tradeoff
- Randomization in survival analysis
This page was built for publication: Randomization in the two-armed bandit problem
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q750006)
