Optimal Behavior is Easier to Learn than the Truth

Minds and Machines 26 (3):243-252 (2016)
  Copy   BIBTEX

Abstract

We consider a reinforcement learning setting where the learner is given a set of possible models containing the true model. While there are algorithms that are able to successfully learn optimal behavior in this setting, they do so without trying to identify the underlying true model. Indeed, we show that there are cases in which the attempt to find the true model is doomed to failure.

Categories

Keywords

Reprint years

DOI

10.1007/s11023-016-9389-y

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 94,045

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

Toward a Psychology of Deep Reinforcement Learning Agents Using a Cognitive Architecture.Konstantinos Mitsopoulos, Sterling Somers, Joel Schooler, Christian Lebiere, Peter Pirolli & Robert Thomson - 2022 - Topics in Cognitive Science 14 (4):756-779.
SA w_ S _u: An Integrated Model of Associative and Reinforcement Learning.Vladislav D. Veksler, Christopher W. Myers & Kevin A. Gluck - 2014 - Cognitive Science 38 (3):580-598.
Evidence for Learning to Learn Behavior in Normal Form Games.Timothy C. Salmon - 2004 - Theory and Decision 56 (4):367-404.
経験に固執しない Profit Sharing 法.Ueno Atsushi Uemura Wataru - 2006 - Transactions of the Japanese Society for Artificial Intelligence 21:81-93.
Conditional Learning Through Causal Models.Jonathan Vandenburgh - 2020 - Synthese (1-2):2415-2437.
Are People Successful at Learning Sequences of Actions on a Perceptual Matching Task?Reiko Yakushijin & Robert A. Jacobs - 2011 - Cognitive Science 35 (5):939-962.
Truth-Tracking by Belief Revision.Alexandru Baltag, Nina Gierasimczuk & Sonja Smets - 2019 - Studia Logica 107 (5):917-947.
Exploration and Exploitation During Sequential Search.Gregory Dam & Konrad Körding - 2009 - Cognitive Science 33 (3):530-541.
The Outcome‐Representation Learning Model: A Novel Reinforcement Learning Model of the Iowa Gambling Task.Nathaniel Haines, Jasmin Vassileva & Woo-Young Ahn - 2018 - Cognitive Science 42 (8):2534-2561.
Reinforcement Learning for Production‐Based Cognitive Models.Adrian Brasoveanu & Jakub Dotlačil - 2021 - Topics in Cognitive Science 13 (3):467-487.

Analytics

Added to PP
2016-02-03

Downloads
37 (#420,955)

6 months
26 (#139,589)

Historical graph of downloads
How can I increase my downloads?

Citations of this work

No citations found.

Add more citations

References found in this work

Pragmatism: A New Name for Some Old Ways of Thinking.William James - 2014 - Gorham, ME: Cambridge University Press. Edited by Eric C. Sheffield.
Pragmatism.William James - 1922 - New York [etc.]: Longmans, Green and co.. Edited by William James & Doris Olin.

Add more references