Bayesian Analysis, Endogenous Data,and Convergence of Beliefs
Problems in statistical analysis, economics, and many other disciplines often involve a trade-off between rewards and additional information that could yield higher future rewards. This thesis investigates such a trade-off, using a class of problems known as bandit problems. In these problems, a rew...
Main Author: | Foerster, Andrew T. |
---|---|
Format: | Others |
Published: |
VCU Scholars Compass
2006
|
Subjects: | |
Online Access: | http://scholarscompass.vcu.edu/etd/1477 http://scholarscompass.vcu.edu/cgi/viewcontent.cgi?article=2476&context=etd |
Similar Items
-
PAC-Bayesian aggregation and multi-armed bandits
by: Audibert, Jean-Yves
Published: (2010) -
A Study of Thompson Sampling Approach for the Sleeping Multi-Armed Bandit Problem
by: Chatterjee, Aritra
Published: (2018) -
Apprentissage pour le contrôle de plateformes parallèles à large échelle
by: Reis, Valentin
Published: (2018) -
Contextual Bandit Learning With Reward Oracles and Sampling Guidance in Multi-Agent Environments
by: Mike Li, et al.
Published: (2021-01-01) -
Minimizing age of information for semi-periodic arrivals of multiple packets
by: Chen, Mianlong
Published: (2019)