{"id":"https://openalex.org/W1538757073","doi":"https://doi.org/10.1109/icmla.2004.1383493","title":"A Bayesian technique for task localization in multiple goal Markov decision processes","display_name":"A Bayesian technique for task localization in multiple goal Markov decision processes","publication_year":2005,"publication_date":"2005-04-06","ids":{"openalex":"https://openalex.org/W1538757073","doi":"https://doi.org/10.1109/icmla.2004.1383493","mag":"1538757073"},"language":"en","primary_location":{"id":"doi:10.1109/icmla.2004.1383493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2004.1383493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 International Conference on Machine Learning and Applications, 2004. Proceedings.","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111897802","display_name":"James L. Carroll","orcid":"https://orcid.org/0000-0002-6152-4911"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.L. Carroll","raw_affiliation_strings":["Brigham Young University, Provo, UT, USA","Brigham Young University Provo, UT 84602 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]},{"raw_affiliation_string":"Brigham Young University Provo, UT 84602 USA","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029074659","display_name":"Kevin Seppi","orcid":"https://orcid.org/0000-0002-4932-2700"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Seppi","raw_affiliation_strings":["Brigham Young University, Provo, UT, USA","Brigham Young University Provo, UT 84602 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]},{"raw_affiliation_string":"Brigham Young University Provo, UT 84602 USA","institution_ids":["https://openalex.org/I100005738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I100005738"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"49","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.8047850131988525},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7746256589889526},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7716590166091919},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.729577362537384},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6712016463279724},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6316573023796082},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6286654472351074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6037255525588989},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5735473036766052},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48181191086769104},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4670772850513458},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45277833938598633},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3679382801055908},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2685733437538147},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11436223983764648},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08110648393630981},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05347767472267151}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.8047850131988525},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7746256589889526},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716590166091919},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.729577362537384},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6712016463279724},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6316573023796082},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6286654472351074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6037255525588989},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5735473036766052},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48181191086769104},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4670772850513458},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45277833938598633},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3679382801055908},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2685733437538147},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11436223983764648},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08110648393630981},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05347767472267151},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icmla.2004.1383493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2004.1383493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 International Conference on Machine Learning and Applications, 2004. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarsarchive.byu.edu:facpub-2033","is_oa":false,"landing_page_url":"https://scholarsarchive.byu.edu/facpub/1034","pdf_url":null,"source":{"id":"https://openalex.org/S4377196308","display_name":"ScholarsArchive  (Brigham Young University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I100005738","host_organization_name":"Brigham Young University","host_organization_lineage":["https://openalex.org/I100005738"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.79.3348","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.79.3348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://james.jlcarroll.net/publications/localization6.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W107715831","https://openalex.org/W121337034","https://openalex.org/W1255659923","https://openalex.org/W1258105458","https://openalex.org/W1499408472","https://openalex.org/W1560550898","https://openalex.org/W1591803298","https://openalex.org/W1598748993","https://openalex.org/W1621791442","https://openalex.org/W1991564165","https://openalex.org/W1996847178","https://openalex.org/W2006258746","https://openalex.org/W2107726111","https://openalex.org/W2122451452","https://openalex.org/W2172405120","https://openalex.org/W2797328151","https://openalex.org/W6604329173","https://openalex.org/W6627930527","https://openalex.org/W6628107543","https://openalex.org/W6633555322","https://openalex.org/W6635327058","https://openalex.org/W6655340590"],"related_works":["https://openalex.org/W3123911006","https://openalex.org/W4400868993","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W3096874164","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W1985560493","https://openalex.org/W2386410636"],"abstract_inverted_index":{"In":[0],"a":[1,25,48,52],"reinforcement":[2],"learning":[3],"task":[4,17,27],"library":[5,32],"system":[6],"for":[7],"Multiple":[8],"Goal":[9],"Markov":[10],"Decision":[11],"Process":[12],"(MGMDP),":[13],"localization":[14,41],"in":[15,30,33,42],"the":[16,20,57],"space":[18],"allows":[19],"agent":[21],"to":[22,35],"determine":[23],"whether":[24],"given":[26],"is":[28],"already":[29],"its":[31],"order":[34],"exploit":[36],"previously":[37],"learned":[38],"experience.":[39],"Task":[40,70],"MGMDPs":[43],"can":[44,64],"be":[45,65],"accomplished":[46],"through":[47,67],"Bayesian":[49,69],"approach,":[50],"however":[51],"trivial":[53],"approach":[54],"fails":[55],"when":[56],"rewards":[58],"are":[59],"not":[60],"distributed":[61],"normally.":[62],"This":[63],"overcome":[66],"our":[68],"Localization":[71],"Technique":[72],"(BTLT).":[73]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}