Relative entropy in sequential decision problems

DOI10.1016/S0304-4068(99)00027-0zbMath0952.91019WikidataQ126340702 ScholiaQ126340702MaRDI QIDQ1567189

Rann Smorodinsky, Ehud Lehrer

Publication date: 5 June 2000

Published in: Journal of Mathematical Economics (Search for Journal in Brave)

zbMATH Keywords

optimizationrelative entropysequential decision problems

Mathematics Subject Classification ID

Decision theory (91B06)

Related Items (11)

Prior symmetry, similarity-based reasoning, and endogenous categorization ⋮ Nonmanipulable Bayesian testing ⋮ Some small deviation theorems for arbitrary continuous random sequence ⋮ A NECESSARY AND SUFFICIENT CONDITION FOR CONVERGENCE OF STATISTICAL TO STRATEGIC EQUILIBRIA OF MARKET GAMES ⋮ Entropy bounds on Bayesian learning ⋮ Learning the fundamentals in a stationary environment ⋮ Informationally optimal correlation ⋮ ENTROPIES OF FUZZY INDISCERNIBILITY RELATION AND ITS OPERATIONS ⋮ Some limit theorems of runs to the continuous‐valued sequence ⋮ On Strong Deviation Theorems Concerning Arrays of Non-Negative Integer-Valued Random Variables ⋮ How to play with a biased coin?

Cites Work

• Unnamed Item
• Unnamed Item
• A Mathematical Theory of Communication
• Repeated games with stationary bounded recall strategies
• Weak and strong merging of opinions
• Bayesian learning leads to correlated equilibria in normal form games
• Repeated large games with incomplete information
• Does rational learning lead to Nash equilibrium in finitely repeated games?
• Necessary and sufficient conditions for convergence to Nash equilibrium: The almost absolute continuity hypothesis
• Rational Learning Leads to Nash Equilibrium
• Merging of Opinions with Increasing Information
• Asset Prices in an Exchange Economy
• Do Markets Favor Agents able to Make Accurate Predictions?
• Compatible Measures and Merging

This page was built for publication: Relative entropy in sequential decision problems