2026-07-20T06:35:51Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:1741 2024-03-06T10:33:07Z ddc:004 open_access

Solvency Games Berger, Noam Kapur, Nevin Schulman, Leonard Vazirani, Vijay Decision making under uncertainity multi-arm bandit problems game theory We study the decision theory of a maximally risk-averse investor --- one whose objective, in the face of stochastic uncertainties, is to minimize the probability of ever going broke. With a view to developing the mathematical basics of such a theory, we start with a very simple model and obtain the following results: a characterization of best play by investors; an explanation of why poor and rich players may have different best strategies; an explanation of why expectation-maximization is not necessarily the best strategy even for rich players. For computation of optimal play, we show how to apply the Value Iteration method, and prove a bound on its convergence rate. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Noam Berger and Nevin Kapur and Leonard Schulman and Vijay Vazirani 2008 Is Part Of LIPIcs, Volume 2, IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science (2008) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.FSTTCS.2008.1741 urn:nbn:de:0030-drops-17419 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FSTTCS.2008.1741 eng https://creativecommons.org/licenses/by-nc-nd/3.0/legalcode