Automatically assigned DDC number: 00631
Manually assigned DDC number: 00631
Number of references: 8
Title: Model based Bayesian Exploration
Author:
Author:
Author:
Subject: Richard Dearden,Nir Friedman,David Andre Model based Bayesian Exploration
Description: Reinforcement learning systems are often concerned with balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of exploration can be estimated using the classical notion of Value of Information --- the expected improvement in future decision quality arising from the information acquired by exploration. Estimating this quantity requires an assessment of the agent's uncertainty about its current value estimates for states. In this paper we investigate ways to represent and reason about this uncertainty in algorithms where the system attempts to learn a model of its environment. We explicitly represent uncertainty about the parameters of the model and build probability distributions over Qvalues based on these. These distributions are used to compute a myopic approximation to the value of information for each action and hence to select the action that best balances exploration and exploitation. 1 Introduction Reinforcement learnin...
Contributor: The Pennsylvania State University CiteSeer Archives
Publisher: unknown
Date: 1999-06-23
Pubyear: 1999
Format: ps
Identifier: http://citeseer.ist.psu.edu/201945.html
Source: http://www.cs.ubc.ca/spider/dearden/Papers/_download_/modelLearn.ps.gz
Language: en
Relation:
Relation:
Relation:
Relation:
Relation:
Relation:
Relation:
Relation:
Rights: unrestricted
<?xml version="1.0" encoding="UTF-8"?>
<references_metadata>
<rec ID="/14093.html" Type="misc" CiteSeer_Book="" CiteSeer_Volume="" Title="Generalized Prioritized Sweeping,">
<identifier Org="ISBN:1558607072" Paper_ID="/14093.html" Extracted="1558607072" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.3333333333333333" />
<identifier Org="ISBN:1558607781" Paper_ID="/14093.html" Extracted="1558607781" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.3333333333333333" />
<identifier Org="ISBN:1599047055" Paper_ID="/14093.html" Extracted="1599047055" DDC="006.3/33" Normalized_DDC="006333" Normalized_Weight="0.3333333333333333" />
<identifier Org="ISBN:3540695729" Paper_ID="/14093.html" Extracted="3540695729" />
</rec>
<rec ID="/18504.html" Type="inproceedings" CiteSeer_Book="AAAIIAAI" CiteSeer_Volume="" Title="Bayesian Q-Learning,">
<identifier Org="ISBN:0199216096" Paper_ID="/18504.html" Extracted="0199216096" DDC="153" Normalized_DDC="153" Normalized_Weight="0.125" />
<identifier Org="ISBN:0262201526" Paper_ID="/18504.html" Extracted="0262201526" />
<identifier Org="ISBN:0262510987" Paper_ID="/18504.html" Extracted="0262510987" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.125" />
<identifier Org="ISBN:1558607072" Paper_ID="/18504.html" Extracted="1558607072" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.125" />
<identifier Org="ISBN:1558607781" Paper_ID="/18504.html" Extracted="1558607781" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.125" />
<identifier Org="ISBN:1846283515" Paper_ID="/18504.html" Extracted="1846283515" DDC="658.312402854678" Normalized_DDC="658312402854678" Normalized_Weight="0.125" />
<identifier Org="ISBN:3540201211" Paper_ID="/18504.html" Extracted="3540201211" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.125" />
<identifier Org="ISBN:3540695729" Paper_ID="/18504.html" Extracted="3540695729" />
<identifier Org="ISBN:3540766308" Paper_ID="/18504.html" Extracted="3540766308" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.125" />
<identifier Org="ISBN:354079865X" Paper_ID="/18504.html" Extracted="354079865X" DDC="006.31" Normalized_DDC="00631" Normalized_Weight="0.125" />
<identifier Org="ISBN:3540897216" Paper_ID="/18504.html" Extracted="3540897216" />
</rec>
<rec ID="/192220.html" Type="misc" CiteSeer_Book="" CiteSeer_Volume="" Title="Efficient bayesian parameter estimation in large discrete domains,">
<identifier Org="ISBN:026204207X" Paper_ID="/192220.html" Extracted="026204207X" />
<identifier Org="ISBN:0262112450" Paper_ID="/192220.html" Extracted="0262112450" />
<identifier Org="ISBN:1558607072" Paper_ID="/192220.html" Extracted="1558607072" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="1.0" />
</rec>
<rec ID="/595474.html" Type="misc" CiteSeer_Book="" CiteSeer_Volume="" Title="A tutorial on learning with bayesian networks,">
<identifier Org="ISBN:0262072882" Paper_ID="/595474.html" Extracted="0262072882" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:0262511290" Paper_ID="/595474.html" Extracted="0262511290" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:0262600323" Paper_ID="/595474.html" Extracted="0262600323" DDC="519.5" Normalized_DDC="5195" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:0262731444" Paper_ID="/595474.html" Extracted="0262731444" DDC="153.03" Normalized_DDC="15303" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:0769520383" Paper_ID="/595474.html" Extracted="0769520383" />
<identifier Org="ISBN:1558604804" Paper_ID="/595474.html" Extracted="1558604804" />
<identifier Org="ISBN:1586037749" Paper_ID="/595474.html" Extracted="1586037749" DDC="610.285" Normalized_DDC="610285" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3527318224" Paper_ID="/595474.html" Extracted="3527318224" DDC="572.8636" Normalized_DDC="5728636" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540005676" Paper_ID="/595474.html" Extracted="3540005676" DDC="005.1/15" Normalized_DDC="005115" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540201211" Paper_ID="/595474.html" Extracted="3540201211" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540230920" Paper_ID="/595474.html" Extracted="3540230920" DDC="004/.35" Normalized_DDC="00435" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540231226" Paper_ID="/595474.html" Extracted="3540231226" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540233563" Paper_ID="/595474.html" Extracted="3540233563" DDC="006.31" Normalized_DDC="00631" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540258965" Paper_ID="/595474.html" Extracted="3540258965" DDC="005.8" Normalized_DDC="0058" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540425381" Paper_ID="/595474.html" Extracted="3540425381" DDC="005.1/15" Normalized_DDC="005115" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540437819" Paper_ID="/595474.html" Extracted="3540437819" DDC="670/.285/63" Normalized_DDC="67028563" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540677976" Paper_ID="/595474.html" Extracted="3540677976" DDC="004/.01/5113" Normalized_DDC="004015113" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540678395" Paper_ID="/595474.html" Extracted="3540678395" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540850651" Paper_ID="/595474.html" Extracted="3540850651" />
<identifier Org="ISBN:427490525X" Paper_ID="/595474.html" Extracted="427490525X" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.058823529411764705" />
</rec>
<rec ID="/369935.html" Type="article" CiteSeer_Book="Journal of Artificial Intelligence Research" CiteSeer_Volume="4" Title="Reinforcement Learning: A Survey,">
<identifier Org="ISBN:0262193981" Paper_ID="/369935.html" Extracted="0262193981" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:0262541041" Paper_ID="/369935.html" Extracted="0262541041" DDC="005.1/15" Normalized_DDC="005115" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:0262731444" Paper_ID="/369935.html" Extracted="0262731444" DDC="153.03" Normalized_DDC="15303" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:047166054X" Paper_ID="/369935.html" Extracted="047166054X" DDC="519.7/03" Normalized_DDC="519703" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:1586030787" Paper_ID="/369935.html" Extracted="1586030787" DDC="629.8/9263" Normalized_DDC="62989263" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:1586032399" Paper_ID="/369935.html" Extracted="1586032399" DDC="629.8/9263" Normalized_DDC="62989263" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:1586034146" Paper_ID="/369935.html" Extracted="1586034146" DDC="629.8/9263" Normalized_DDC="62989263" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540231056" Paper_ID="/369935.html" Extracted="3540231056" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540233563" Paper_ID="/369935.html" Extracted="3540233563" DDC="006.31" Normalized_DDC="00631" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540252606" Paper_ID="/369935.html" Extracted="3540252606" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:354027894X" Paper_ID="/369935.html" Extracted="354027894X" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:354029046X" Paper_ID="/369935.html" Extracted="354029046X" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540422196" Paper_ID="/369935.html" Extracted="3540422196" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540422358" Paper_ID="/369935.html" Extracted="3540422358" DDC="573.8" Normalized_DDC="5738" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540673547" Paper_ID="/369935.html" Extracted="3540673547" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540723463" Paper_ID="/369935.html" Extracted="3540723463" DDC="004.019" Normalized_DDC="004019" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540746897" Paper_ID="/369935.html" Extracted="3540746897" />
<identifier Org="ISBN:3540747680" Paper_ID="/369935.html" Extracted="3540747680" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.058823529411764705" />
<identifier Org="ISBN:3540751181" Paper_ID="/369935.html" Extracted="3540751181" />
</rec>
<rec ID="/44268.html" Type="inproceedings" CiteSeer_Book="" CiteSeer_Volume="" Title="Stochastic simulation algorithms for dynamic probabilistic networks,">
<identifier Org="ISBN:0121197921" Paper_ID="/44268.html" Extracted="0121197921" DDC="621.36/7" Normalized_DDC="621367" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:0198510551" Paper_ID="/44268.html" Extracted="0198510551" DDC="003/.76" Normalized_DDC="00376" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:0262510987" Paper_ID="/44268.html" Extracted="0262510987" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:0262600323" Paper_ID="/44268.html" Extracted="0262600323" DDC="519.5" Normalized_DDC="5195" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:078032983X" Paper_ID="/44268.html" Extracted="078032983X" />
<identifier Org="ISBN:0805849912" Paper_ID="/44268.html" Extracted="0805849912" DDC="153" Normalized_DDC="153" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:0821826972" Paper_ID="/44268.html" Extracted="0821826972" DDC="510" Normalized_DDC="51" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:1558603859" Paper_ID="/44268.html" Extracted="1558603859" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:1558604855" Paper_ID="/44268.html" Extracted="1558604855" />
<identifier Org="ISBN:1558606114" Paper_ID="/44268.html" Extracted="1558606114" />
<identifier Org="ISBN:1568811551" Paper_ID="/44268.html" Extracted="1568811551" DDC="629.8/92" Normalized_DDC="629892" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:1581130570" Paper_ID="/44268.html" Extracted="1581130570" />
<identifier Org="ISBN:1584883871" Paper_ID="/44268.html" Extracted="1584883871" DDC="519.5/42" Normalized_DDC="519542" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540231226" Paper_ID="/44268.html" Extracted="3540231226" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540235272" Paper_ID="/44268.html" Extracted="3540235272" DDC="006.4" Normalized_DDC="0064" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540415874" Paper_ID="/44268.html" Extracted="3540415874" DDC="658.4/034" Normalized_DDC="6584034" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540643419" Paper_ID="/44268.html" Extracted="3540643419" DDC="006.3/2" Normalized_DDC="00632" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:354064413X" Paper_ID="/44268.html" Extracted="354064413X" DDC="003/.54" Normalized_DDC="00354" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540664289" Paper_ID="/44268.html" Extracted="3540664289" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.06666666666666667" />
</rec>
<rec ID="/100536.html" Type="inproceedings" CiteSeer_Book="Proc 15th International Conf on Machine Learning" CiteSeer_Volume="" Title="Using learning for approximation in stochastic processes,">
<identifier Org="ISBN:0262042061" Paper_ID="/100536.html" Extracted="0262042061" />
<identifier Org="ISBN:0262194503" Paper_ID="/100536.html" Extracted="0262194503" />
<identifier Org="ISBN:0387951466" Paper_ID="/100536.html" Extracted="0387951466" DDC="519.2/82" Normalized_DDC="519282" Normalized_Weight="0.3333333333333333" />
<identifier Org="ISBN:0769524885" Paper_ID="/100536.html" Extracted="0769524885" />
<identifier Org="ISBN:1568811551" Paper_ID="/100536.html" Extracted="1568811551" DDC="629.8/92" Normalized_DDC="629892" Normalized_Weight="0.3333333333333333" />
<identifier Org="ISBN:1586036424" Paper_ID="/100536.html" Extracted="1586036424" />
<identifier Org="ISBN:3540664955" Paper_ID="/100536.html" Extracted="3540664955" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.3333333333333333" />
<identifier Org="ISBN:3866110383" Paper_ID="/100536.html" Extracted="3866110383" />
<identifier Org="ISBN:9999905331" Paper_ID="/100536.html" Extracted="9999905331" />
</rec>
<rec ID="/28964.html" Type="article" CiteSeer_Book="Machine Learning" CiteSeer_Volume="13" Title="Prioritized Sweeping: Reinforcement Learning With Less Data and Less Time,">
<identifier Org="ISBN:0262112450" Paper_ID="/28964.html" Extracted="0262112450" />
<identifier Org="ISBN:0262511290" Paper_ID="/28964.html" Extracted="0262511290" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:0262661446" Paper_ID="/28964.html" Extracted="0262661446" DDC="591.5/01/1" Normalized_DDC="5915011" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:0792345843" Paper_ID="/28964.html" Extracted="0792345843" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:1558603700" Paper_ID="/28964.html" Extracted="1558603700" DDC="005.1" Normalized_DDC="0051" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:1558604170" Paper_ID="/28964.html" Extracted="1558604170" />
<identifier Org="ISBN:1558607072" Paper_ID="/28964.html" Extracted="1558607072" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:1558607781" Paper_ID="/28964.html" Extracted="1558607781" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:157735236X" Paper_ID="/28964.html" Extracted="157735236X" />
<identifier Org="ISBN:3540000119" Paper_ID="/28964.html" Extracted="3540000119" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:3540206469" Paper_ID="/28964.html" Extracted="3540206469" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:3540221395" Paper_ID="/28964.html" Extracted="3540221395" DDC="006.3'1" Normalized_DDC="00631" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:3540231056" Paper_ID="/28964.html" Extracted="3540231056" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:3540415971" Paper_ID="/28964.html" Extracted="3540415971" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:3540440380" Paper_ID="/28964.html" Extracted="3540440380" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:3540678395" Paper_ID="/28964.html" Extracted="3540678395" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:3540688463" Paper_ID="/28964.html" Extracted="3540688463" />
<identifier Org="ISBN:3540695729" Paper_ID="/28964.html" Extracted="3540695729" />
<identifier Org="ISBN:3790813486" Paper_ID="/28964.html" Extracted="3790813486" DDC="794.8/151" Normalized_DDC="7948151" Normalized_Weight="0.07142857142857142" />
</rec>
<rec ID="SELF" Type="SELF" CiteSeer_Book="SELF" CiteSeer_Volume="SELF" Title="Model based Bayesian Exploration">
<identifier Org="ISBN:026204207X" Paper_ID="SELF" Extracted="026204207X" />
<identifier Org="ISBN:0262701146" Paper_ID="SELF" Extracted="0262701146" DDC="629.8/92" Normalized_DDC="629892" Normalized_Weight="0.1" />
<identifier Org="ISBN:1558607072" Paper_ID="SELF" Extracted="1558607072" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.1" />
<identifier Org="ISBN:1558607781" Paper_ID="SELF" Extracted="1558607781" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.1" />
<identifier Org="ISBN:3540201211" Paper_ID="SELF" Extracted="3540201211" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.1" />
<identifier Org="ISBN:3540231056" Paper_ID="SELF" Extracted="3540231056" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.1" />
<identifier Org="ISBN:3540250735" Paper_ID="SELF" Extracted="3540250735" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.1" />
<identifier Org="ISBN:3540749578" Paper_ID="SELF" Extracted="3540749578" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.1" />
<identifier Org="ISBN:3540758526" Paper_ID="SELF" Extracted="3540758526" DDC="004.6/2" Normalized_DDC="00462" Normalized_Weight="0.1" />
<identifier Org="ISBN:3540766308" Paper_ID="SELF" Extracted="3540766308" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.1" />
<identifier Org="ISBN:3540858334" Paper_ID="SELF" Extracted="3540858334" />
<identifier Org="ISBN:3540928022" Paper_ID="SELF" Extracted="3540928022" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.1" />
</rec>
</references_metadata>