Skip navigation
Skip navigation
Open Research will be down for maintenance between 8:00 and 8:15 am on Tuesday, December 1 2020.

Death and suicide in universal artificial intelligence

Martin, Jarryd; Everitt, Tom; Hutter, Marcus

Description

Reinforcement learning (RL) is a general paradigm for studying intelligent behaviour, with applications ranging from artificial intelligence to psychology and economics. AIXI is a universal solution to the RL problem; it can learn any computable environment. A technical subtlety of AIXI is that it is defined using a mixture over semimeasures that need not sum to 1, rather than over proper probability measures. In this work we argue that the shortfall of a semimeasure can naturally be...[Show more]

dc.contributor.authorMartin, Jarryd
dc.contributor.authorEveritt, Tom
dc.contributor.authorHutter, Marcus
dc.date.accessioned2016-12-21T00:53:45Z
dc.date.available2016-12-21T00:53:45Z
dc.identifier.isbn978-3-319-41648-9
dc.identifier.issn0302-9743
dc.identifier.urihttp://hdl.handle.net/1885/111443
dc.description.abstractReinforcement learning (RL) is a general paradigm for studying intelligent behaviour, with applications ranging from artificial intelligence to psychology and economics. AIXI is a universal solution to the RL problem; it can learn any computable environment. A technical subtlety of AIXI is that it is defined using a mixture over semimeasures that need not sum to 1, rather than over proper probability measures. In this work we argue that the shortfall of a semimeasure can naturally be interpreted as the agent’s estimate of the probability of its death. We formally define death for generally intelligent agents like AIXI, and prove a number of related theorems about their behaviour. Notable discoveries include that agent behaviour can change radically under positive linear transformations of the reward signal (from suicidal to dogmatically self-preserving), and that the agent’s posterior belief that it will survive increases over time.
dc.format23 pages
dc.format.mimetypeapplication/pdf
dc.publisherSpringer Verlag (Germany)
dc.rights© Springer International Publishing Switzerland 2016
dc.sourceLecture Notes in Computer Science
dc.subjectreinforcement learning (RL)
dc.subjectsemimeasure
dc.subjectintelligent
dc.subjectbehaviour
dc.subjectartificial
dc.subjectintelligence
dc.subjectAIXI
dc.subjectdeath
dc.subjectprobability
dc.titleDeath and suicide in universal artificial intelligence
dc.typeJournal article
local.description.notesThe article appears as part of a monographic series in Steunebrink B., Wang P., Goertzel B. (eds) Artificial General Intelligence. AGI 2016. Lecture Notes in Computer Science, vol 9782. Springer, Cham.
local.identifier.citationvolume9782
dc.date.issued2016-06-25
local.publisher.urlhttp://link.springer.com/
local.type.statusPublished Version
local.contributor.affiliationHutter, Marcus, Research School of Computer Science, College of Engineering and Computer Science, The Australian National University
local.bibliographicCitation.startpage23
local.bibliographicCitation.lastpage32
local.identifier.doi10.1007/978-3-319-41649-6_3
dcterms.accessRightsOpen Access
CollectionsANU Research Publications

Download

There are no files associated with this item.


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