Optimism in the face of uncertainty should be refutable

Minds and Machines 18 (4):521-526 (2008)
  Copy   BIBTEX

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.

Categories

Keywords

Reprint years

DOI

10.1007/s11023-008-9115-5

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 93,642

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

My notes

Similar books and articles

Reinforcement learning of non-Markov decision processes.Steven D. Whitehead & Long-Ji Lin - 1995 - Artificial Intelligence 73 (1-2):271-306.
Bounded-parameter Markov decision processes.Robert Givan, Sonia Leach & Thomas Dean - 2000 - Artificial Intelligence 122 (1-2):71-109.
Optimal Behavior is Easier to Learn than the Truth.Ronald Ortner - 2016 - Minds and Machines 26 (3):243-252.
Equivalence notions and model minimization in Markov decision processes.Robert Givan, Thomas Dean & Matthew Greig - 2003 - Artificial Intelligence 147 (1-2):163-223.
Qualitative Axioms of Uncertainty as a Foundation for Probability and Decision-Making.Patrick Suppes - 2016 - Minds and Machines 26 (2):185-202.
Partially observable Markov decision processes with imprecise parameters.Hideaki Itoh & Kiyohiko Nakamura - 2007 - Artificial Intelligence 171 (8-9):453-490.
A Qualitative Linear Utility Theory for Spohn's Theory of Epistemic Beliefs.Phan H. Giang & Prakash P. Shenoy - 2000 - In C. Boutilier & M. Goldszmidt (eds.), Uncertainty in Artificial Intelligence 16. Morgan Kaufmann.
Reachability analysis of uncertain systems using bounded-parameter Markov decision processes.Xenofon di WuKoutsoukos - 2008 - Artificial Intelligence 172 (8-9):945-954.
Real-time dynamic programming for Markov decision processes with imprecise probabilities.Karina V. Delgado, Leliane N. de Barros, Daniel B. Dias & Scott Sanner - 2016 - Artificial Intelligence 230 (C):192-223.
Qualitative Axioms of Uncertainty as a Foundation for Probability and Decision-Making.Patrick Suppes - 2016 - Minds and Machines 26 (1-2):185-202.

Analytics

Added to PP
2009-01-28

Downloads
5 (#1,562,871)

6 months
100 (#50,248)

Historical graph of downloads
How can I increase my downloads?

Citations of this work

Optimal Behavior is Easier to Learn than the Truth.Ronald Ortner - 2016 - Minds and Machines 26 (3):243-252.

Add more citations

References found in this work

Logik der Forschung.Karl R. Popper (ed.) - 1966 - Wien: Mohr (Siebeck).
Logik der Forschung.Karl Popper - 1934 - Erkenntnis 5 (1):290-294.
Logik der Forschung. [REVIEW]E. N. - 1935 - Journal of Philosophy 32 (4):107-108.

Add more references