Mean and variance responsive learning

Decision makers are often described as seeking higher expected payoffs and avoiding higher variance in payoffs. We provide some necessary and some sufficient conditions for learning rules, that assume the agent has little prior and feedback information about the environment, to reflect such preferen...

Full description

Saved in:
Bibliographic Details
Published in:Games and economic behavior 2012-07, Vol.75 (2), p.855-866
Main Authors: Oyarzun, Carlos, Sarin, Rajiv
Format: Article
Language:English
Subjects:
Agency theory
Decision making
Decision making models
Expectation
Information economics
Learning
Mean and variance preferences
Pay-off
Payoffs
Preferences
Reinforcement learning
Studies
Variance
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c422t-9f0fae4aa33c62df1a7a9693f0108bd968aaa50d04b89b1a6ecd46ebae8e610c3
cites cdi_FETCH-LOGICAL-c422t-9f0fae4aa33c62df1a7a9693f0108bd968aaa50d04b89b1a6ecd46ebae8e610c3
container_end_page 866
container_issue 2
container_start_page 855
container_title Games and economic behavior
container_volume 75
creator Oyarzun, Carlos
Sarin, Rajiv
description Decision makers are often described as seeking higher expected payoffs and avoiding higher variance in payoffs. We provide some necessary and some sufficient conditions for learning rules, that assume the agent has little prior and feedback information about the environment, to reflect such preferences. We adopt the framework of Börgers, Morales and Sarin (2004, Econometrica) who provide similar results for learning rules that seek higher expected payoffs. Our analysis reveals that a concern for variance leads to quadratic transformations of payoffs to appear in the learning rule.
doi_str_mv 10.1016/j.geb.2012.02.013
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1022118154</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0899825612000334</els_id><sourcerecordid>1022118154</sourcerecordid><originalsourceid>FETCH-LOGICAL-c422t-9f0fae4aa33c62df1a7a9693f0108bd968aaa50d04b89b1a6ecd46ebae8e610c3</originalsourceid><addsrcrecordid>eNp9kE9Lw0AQxRdRsFY_gLeACF4SZzbJdoMnEf9BxYuel8lmUja0m7rbFvz2bqknD8KDufzeY94T4hKhQEB1OxQLbgsJKAtIwvJITBAayGU1K4_FBHTT5FrW6lScxTgAQC1nMBHXb0w-I99lOwqOvOUscFyPProdZ0um4J1fnIuTnpaRL37vVHw-PX48vOTz9-fXh_t5bispN3nTQ09cEZWlVbLrkWbUqKbsAUG3XaM0EdXQQdXqpkVSbLtKcUusWSHYcipuDrnrMH5tOW7MykXLyyV5HrfRIEiJqLGuEnr1Bx3GbfDpu0RhKqor0InCA2XDGGPg3qyDW1H4TtCeU2YwaTizH85AEpbJc3fwcGq6cxxMtI7TMp0LbDemG90_7h9ruHQ3</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1012568408</pqid></control><display><type>article</type><title>Mean and variance responsive learning</title><source>International Bibliography of the Social Sciences (IBSS)</source><source>ScienceDirect Freedom Collection</source><creator>Oyarzun, Carlos ; Sarin, Rajiv</creator><creatorcontrib>Oyarzun, Carlos ; Sarin, Rajiv</creatorcontrib><description>Decision makers are often described as seeking higher expected payoffs and avoiding higher variance in payoffs. We provide some necessary and some sufficient conditions for learning rules, that assume the agent has little prior and feedback information about the environment, to reflect such preferences. We adopt the framework of Börgers, Morales and Sarin (2004, Econometrica) who provide similar results for learning rules that seek higher expected payoffs. Our analysis reveals that a concern for variance leads to quadratic transformations of payoffs to appear in the learning rule.</description><identifier>ISSN: 0899-8256</identifier><identifier>EISSN: 1090-2473</identifier><identifier>DOI: 10.1016/j.geb.2012.02.013</identifier><language>eng</language><publisher>Duluth: Elsevier Inc</publisher><subject>Agency theory ; Decision making ; Decision making models ; Expectation ; Information economics ; Learning ; Mean and variance preferences ; Pay-off ; Payoffs ; Preferences ; Reinforcement learning ; Studies ; Variance</subject><ispartof>Games and economic behavior, 2012-07, Vol.75 (2), p.855-866</ispartof><rights>2012</rights><rights>Copyright Academic Press Jul 2012</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c422t-9f0fae4aa33c62df1a7a9693f0108bd968aaa50d04b89b1a6ecd46ebae8e610c3</citedby><cites>FETCH-LOGICAL-c422t-9f0fae4aa33c62df1a7a9693f0108bd968aaa50d04b89b1a6ecd46ebae8e610c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925,33223,33224</link.rule.ids></links><search><creatorcontrib>Oyarzun, Carlos</creatorcontrib><creatorcontrib>Sarin, Rajiv</creatorcontrib><title>Mean and variance responsive learning</title><title>Games and economic behavior</title><description>Decision makers are often described as seeking higher expected payoffs and avoiding higher variance in payoffs. We provide some necessary and some sufficient conditions for learning rules, that assume the agent has little prior and feedback information about the environment, to reflect such preferences. We adopt the framework of Börgers, Morales and Sarin (2004, Econometrica) who provide similar results for learning rules that seek higher expected payoffs. Our analysis reveals that a concern for variance leads to quadratic transformations of payoffs to appear in the learning rule.</description><subject>Agency theory</subject><subject>Decision making</subject><subject>Decision making models</subject><subject>Expectation</subject><subject>Information economics</subject><subject>Learning</subject><subject>Mean and variance preferences</subject><subject>Pay-off</subject><subject>Payoffs</subject><subject>Preferences</subject><subject>Reinforcement learning</subject><subject>Studies</subject><subject>Variance</subject><issn>0899-8256</issn><issn>1090-2473</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2012</creationdate><recordtype>article</recordtype><sourceid>8BJ</sourceid><recordid>eNp9kE9Lw0AQxRdRsFY_gLeACF4SZzbJdoMnEf9BxYuel8lmUja0m7rbFvz2bqknD8KDufzeY94T4hKhQEB1OxQLbgsJKAtIwvJITBAayGU1K4_FBHTT5FrW6lScxTgAQC1nMBHXb0w-I99lOwqOvOUscFyPProdZ0um4J1fnIuTnpaRL37vVHw-PX48vOTz9-fXh_t5bispN3nTQ09cEZWlVbLrkWbUqKbsAUG3XaM0EdXQQdXqpkVSbLtKcUusWSHYcipuDrnrMH5tOW7MykXLyyV5HrfRIEiJqLGuEnr1Bx3GbfDpu0RhKqor0InCA2XDGGPg3qyDW1H4TtCeU2YwaTizH85AEpbJc3fwcGq6cxxMtI7TMp0LbDemG90_7h9ruHQ3</recordid><startdate>20120701</startdate><enddate>20120701</enddate><creator>Oyarzun, Carlos</creator><creator>Sarin, Rajiv</creator><general>Elsevier Inc</general><general>Academic Press</general><scope>AAYXX</scope><scope>CITATION</scope><scope>8BJ</scope><scope>FQK</scope><scope>JBE</scope></search><sort><creationdate>20120701</creationdate><title>Mean and variance responsive learning</title><author>Oyarzun, Carlos ; Sarin, Rajiv</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c422t-9f0fae4aa33c62df1a7a9693f0108bd968aaa50d04b89b1a6ecd46ebae8e610c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Agency theory</topic><topic>Decision making</topic><topic>Decision making models</topic><topic>Expectation</topic><topic>Information economics</topic><topic>Learning</topic><topic>Mean and variance preferences</topic><topic>Pay-off</topic><topic>Payoffs</topic><topic>Preferences</topic><topic>Reinforcement learning</topic><topic>Studies</topic><topic>Variance</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Oyarzun, Carlos</creatorcontrib><creatorcontrib>Sarin, Rajiv</creatorcontrib><collection>CrossRef</collection><collection>International Bibliography of the Social Sciences (IBSS)</collection><collection>International Bibliography of the Social Sciences</collection><collection>International Bibliography of the Social Sciences</collection><jtitle>Games and economic behavior</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Oyarzun, Carlos</au><au>Sarin, Rajiv</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Mean and variance responsive learning</atitle><jtitle>Games and economic behavior</jtitle><date>2012-07-01</date><risdate>2012</risdate><volume>75</volume><issue>2</issue><spage>855</spage><epage>866</epage><pages>855-866</pages><issn>0899-8256</issn><eissn>1090-2473</eissn><abstract>Decision makers are often described as seeking higher expected payoffs and avoiding higher variance in payoffs. We provide some necessary and some sufficient conditions for learning rules, that assume the agent has little prior and feedback information about the environment, to reflect such preferences. We adopt the framework of Börgers, Morales and Sarin (2004, Econometrica) who provide similar results for learning rules that seek higher expected payoffs. Our analysis reveals that a concern for variance leads to quadratic transformations of payoffs to appear in the learning rule.</abstract><cop>Duluth</cop><pub>Elsevier Inc</pub><doi>10.1016/j.geb.2012.02.013</doi><tpages>12</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0899-8256
ispartof Games and economic behavior, 2012-07, Vol.75 (2), p.855-866
issn 0899-8256
1090-2473
language eng
recordid cdi_proquest_miscellaneous_1022118154
source International Bibliography of the Social Sciences (IBSS); ScienceDirect Freedom Collection
subjects Agency theory
Decision making
Decision making models
Expectation
Information economics
Learning
Mean and variance preferences
Pay-off
Payoffs
Preferences
Reinforcement learning
Studies
Variance
title Mean and variance responsive learning
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T12%3A23%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Mean%20and%20variance%20responsive%20learning&rft.jtitle=Games%20and%20economic%20behavior&rft.au=Oyarzun,%20Carlos&rft.date=2012-07-01&rft.volume=75&rft.issue=2&rft.spage=855&rft.epage=866&rft.pages=855-866&rft.issn=0899-8256&rft.eissn=1090-2473&rft_id=info:doi/10.1016/j.geb.2012.02.013&rft_dat=%3Cproquest_cross%3E1022118154%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c422t-9f0fae4aa33c62df1a7a9693f0108bd968aaa50d04b89b1a6ecd46ebae8e610c3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1012568408&rft_id=info:pmid/&rfr_iscdi=true