{"id":"https://openalex.org/W1985054922","doi":"https://doi.org/10.1109/adprl.2014.7010633","title":"Pseudo-MDPs and factored linear action models","display_name":"Pseudo-MDPs and factored linear action models","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1985054922","doi":"https://doi.org/10.1109/adprl.2014.7010633","mag":"1985054922"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},"type":"article","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/A5050876115","display_name":"Hengshuai Yao","orcid":"https://orcid.org/0000-0003-1258-1845"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Hengshuai Yao","raw_affiliation_strings":["Department of Computing Science, University of Alberta Edmonton, Alberta, Canada","Department of Computing Science University of Alberta Edmonton, Alberta, Canada, T6G2E8"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science University of Alberta Edmonton, Alberta, Canada, T6G2E8","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069856068","display_name":"Csaba Szepesv\u00e1ri","orcid":"https://orcid.org/0000-0002-9286-2892"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Csaba Szepesvari","raw_affiliation_strings":["Department of Computing Science, University of Alberta Edmonton, Alberta, Canada","Department of Computing Science University of Alberta Edmonton, Alberta, Canada, T6G2E8"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science University of Alberta Edmonton, Alberta, Canada, T6G2E8","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038039948","display_name":"Bernardo \u00c1vila Pires","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bernardo Avila Pires","raw_affiliation_strings":["Department of Computing Science, University of Alberta Edmonton, Alberta, Canada","Department of Computing Science University of Alberta Edmonton, Alberta, Canada, T6G2E8"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science University of Alberta Edmonton, Alberta, Canada, T6G2E8","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100380929","display_name":"Xinhua Zhang","orcid":"https://orcid.org/0000-0002-2767-4908"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xinhua Zhang","raw_affiliation_strings":["Machine Learning Research Group, National ICT Australia Sydney and Canberra, Australia","Machine Learning Research Group National ICT Australia Sydney and Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Machine Learning Research Group, National ICT Australia Sydney and Canberra, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"Machine Learning Research Group National ICT Australia Sydney and Canberra, Australia","institution_ids":["https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050876115"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":1.4623,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.81395195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9923999905586243,"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"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9923999905586243,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9801999926567078,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9397000074386597,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.7846704721450806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387372255325317},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5824576616287231},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5562533736228943},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5342637300491333},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5211256146430969},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4747379422187805},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3339695334434509},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2780526876449585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2644767165184021},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18590793013572693}],"concepts":[{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7846704721450806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387372255325317},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5824576616287231},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5562533736228943},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5342637300491333},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5211256146430969},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4747379422187805},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3339695334434509},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2780526876449585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2644767165184021},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18590793013572693},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/adprl.2014.7010633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.674.6624","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.674.6624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.cecs.anu.edu.au/%7Exzhang/papers/Yaoetal14.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.681.8209","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.681.8209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ualberta.ca/%7Eszepesva/papers/ieee_adprl2014.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W137325057","https://openalex.org/W1550698229","https://openalex.org/W1576452626","https://openalex.org/W1898511152","https://openalex.org/W1978259121","https://openalex.org/W2073384958","https://openalex.org/W2121863487","https://openalex.org/W2134932665","https://openalex.org/W2164278908","https://openalex.org/W2182244178","https://openalex.org/W2586680856","https://openalex.org/W2949361666","https://openalex.org/W4205326910","https://openalex.org/W4211221179","https://openalex.org/W4214717370","https://openalex.org/W4245296547","https://openalex.org/W4285719527","https://openalex.org/W4292363360","https://openalex.org/W6605656211","https://openalex.org/W6685863877"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2953716828","https://openalex.org/W2469820710","https://openalex.org/W2477549100"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,83],"introduce":[4,38],"the":[5,14,17,29,39,50,64,73,81,99,112,120],"concept":[6,40],"of":[7,41,52,75,97],"pseudo-MDPs":[8],"to":[9,21,67],"develop":[10,68],"abstractions.":[11,35],"Pseudo-MDPs":[12],"relax":[13],"requirement":[15],"that":[16,28,111],"transition":[18],"kernel":[19],"has":[20],"be":[22],"a":[23,46,69,89,93],"probability":[24],"kernel.":[25],"We":[26,36,62,87,109],"show":[27],"new":[30],"framework":[31,66],"captures":[32],"many":[33],"existing":[34,58,85],"also":[37],"factored":[42,53,100],"linear":[43,54,101],"action":[44,55],"models;":[45],"special":[47],"case.":[48],"Again,":[49],"relation":[51],"models":[56],"and":[57,92],"works":[59],"are":[60],"discussed.":[61],"use":[63],"general":[65],"theory":[70],"for":[71],"bounding":[72],"suboptimality":[74],"policies":[76],"derived":[77],"from":[78],"pseudo-MDPs.":[79],"Specializing":[80],"framework,":[82],"recover":[84],"results.":[86],"give":[88],"leastsquares":[90],"approach":[91,96,115,122],"constrained":[94,113],"optimization":[95,114],"learning":[98],"model":[102],"as":[103,105],"well":[104],"efficient":[106],"computation":[107],"methods.":[108],"demonstrate":[110],"gives":[116],"better":[117],"performance":[118],"than":[119],"least-squares":[121],"with":[123],"normalization.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}