PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Optimism in the Face of Uncertainty Should be Refutable
Ronald Ortner
Minds and Machines Volume 18, Number 4, pp. 521-526, 2008.

Abstract

We give an example from the theory of Markov decision processes which shows that the ``optimism in the face of uncertainty'' heuristics may fail to make any progress. This is due to the impossibility to falsify a belief that a (transition) probability is larger than 0. Our example shows the utility of Popper's demand of falsifiability of hypotheses in the area of artificial intelligence.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Theory & Algorithms
ID Code:4540
Deposited By:Ronald Ortner
Deposited On:13 March 2009