Skip navigation
Skip navigation

Axioms for Rational Reinforcement Learning

Sunehag, Peter; Hutter, Marcus

Description

We provide a formal, simple and intuitive theory of rational decision making including sequential decisions that affect the environment. The theory has a geometric flavor, which makes the arguments easy to visualize and understand. Our theory is for complete decision makers, which means that they have a complete set of preferences. Our main result shows that a complete rational decision maker implicitly has a probabilistic model of the environment. We have a countable version of this result...[Show more]

dc.contributor.authorSunehag, Peter
dc.contributor.authorHutter, Marcus
dc.coverage.spatialEspoo Finland
dc.date.accessioned2015-12-08T22:45:59Z
dc.date.createdOctober 5-7 2011
dc.identifier.isbn9783642244117
dc.identifier.urihttp://hdl.handle.net/1885/37947
dc.description.abstractWe provide a formal, simple and intuitive theory of rational decision making including sequential decisions that affect the environment. The theory has a geometric flavor, which makes the arguments easy to visualize and understand. Our theory is for complete decision makers, which means that they have a complete set of preferences. Our main result shows that a complete rational decision maker implicitly has a probabilistic model of the environment. We have a countable version of this result that brings light on the issue of countable vs finite additivity by showing how it depends on the geometry of the space which we have preferences over. This is achieved through fruitfully connecting rationality with the Hahn-Banach Theorem. The theory presented here can be viewed as a formalization and extension of the betting odds approach to probability of Ramsey and De Finetti [Ram31, deF37].
dc.publisherSpringer
dc.relation.ispartofseriesInternational Conference on Algorithmic Learning Theory (ALT 2011)
dc.rightsCopyright Information: © Springer-Verlag Berlin Heidelberg 2011. http://www.sherpa.ac.uk/romeo/issn/0302-9743/..."Author's post-print on any open access repository after 12 months after publication" from SHERPA/RoMEO site (as at 20/08/15)
dc.rightsAuthor/s retain copyright
dc.sourceLecture Notes in Artificial Intelligence 6925
dc.source.urihttp://www-alg.ist.hokudai.ac.jp/~thomas/ALT11/alt11.jhtml
dc.subjectKeywords: Additivity; Decision makers; Hahn-Banach theorem; Linear Functional; Probabilistic models; Rational decision making; Rationality; Utility; Algorithms; Banach spaces; Decision making; Decision theory Banach Space; Linear Functional; Probability; Rationality; Utility
dc.titleAxioms for Rational Reinforcement Learning
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2011
local.identifier.absfor080101 - Adaptive Agents and Intelligent Robotics
local.identifier.ariespublicationu4963866xPUB155
local.type.statusPublished Version
local.contributor.affiliationSunehag, Peter, College of Engineering and Computer Science, ANU
local.contributor.affiliationHutter, Marcus, College of Engineering and Computer Science, ANU
local.bibliographicCitation.startpage338
local.bibliographicCitation.lastpage352
local.identifier.doi10.1007/978-3-642-24412-4_27
local.identifier.absseo970108 - Expanding Knowledge in the Information and Computing Sciences
dc.date.updated2016-02-24T11:30:04Z
local.identifier.scopusID2-s2.0-80054095252
dcterms.accessRightsOpen Access
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Sunehag_Axioms_for_Rational_2011.pdf237.84 kBAdobe PDF


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator