Incomplete Learning from Endogenous Data in Dynamic Allocation

DOI10.1111/1468-0262.00170MaRDI QIDQ4530994zbMATH OpenOpenAlexFDO

Authors Monica Brezzi, Tze Leung Lai

Publication date 28 May 2002

Published in Econometrica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1111/1468-0262.00170

zbMATH Keywords

learningtotal discounted rewardendogenous data

Mathematics Subject Classification ID

Statistical methods; economic indices and measures (91B82)

Recommendations

• Optimal Learning with Endogenous Data
• Limit points of endogenous misspecified learning
• The learning component of dynamic allocation indices
• Bayesian economists \dots Bayesian agents. An alternative approach to optimal learning
• Information processing in a three-actions dynamic decision model

Cited in

(8)

• Optimal Learning with Endogenous Data
• Bayesian exploration for approximate dynamic programming
• On incomplete learning and certainty-equivalence control
• Index policies for discounted bandit problems with availability constraints
• On the optimal amount of experimentation in sequential decision problems
• A Bayesian-bandit adaptive design for \(N\)-of-1 clinical trials
• Learning in society
• Optimal learning and experimentation in bandit problems.

This page was built for publication: Incomplete Learning from Endogenous Data in Dynamic Allocation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4530994)