{"id":"https://openalex.org/W3113228036","doi":"https://doi.org/10.1109/access.2020.3045300","title":"Offline Multi-Policy Gradient for Latent Mixture Environments","display_name":"Offline Multi-Policy Gradient for Latent Mixture Environments","publication_year":2020,"publication_date":"2020-12-17","ids":{"openalex":"https://openalex.org/W3113228036","doi":"https://doi.org/10.1109/access.2020.3045300","mag":"3113228036"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3045300","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3045300","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09296301.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09296301.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100373874","display_name":"Xiaoguang Li","orcid":"https://orcid.org/0000-0003-4580-4865"},"institutions":[{"id":"https://openalex.org/I118803816","display_name":"Liaoning University","ror":"https://ror.org/03xpwj629","country_code":"CN","type":"education","lineage":["https://openalex.org/I118803816"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoguang Li","raw_affiliation_strings":["College of Information, Liaoning University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information, Liaoning University, Shenyang, China","institution_ids":["https://openalex.org/I118803816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086044009","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0001-6228-4908"},"institutions":[{"id":"https://openalex.org/I118803816","display_name":"Liaoning University","ror":"https://ror.org/03xpwj629","country_code":"CN","type":"education","lineage":["https://openalex.org/I118803816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["College of Information, Liaoning University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information, Liaoning University, Shenyang, China","institution_ids":["https://openalex.org/I118803816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017241810","display_name":"Lixin Wang","orcid":"https://orcid.org/0000-0003-1502-4665"},"institutions":[{"id":"https://openalex.org/I118803816","display_name":"Liaoning University","ror":"https://ror.org/03xpwj629","country_code":"CN","type":"education","lineage":["https://openalex.org/I118803816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixin Wang","raw_affiliation_strings":["College of Information, Liaoning University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information, Liaoning University, Shenyang, China","institution_ids":["https://openalex.org/I118803816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072406974","display_name":"Ge Yu","orcid":"https://orcid.org/0000-0002-3171-8889"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Yu","raw_affiliation_strings":["College of Computer Science and Engineering, Northeastern University (China), Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Northeastern University (China), Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100373874"],"corresponding_institution_ids":["https://openalex.org/I118803816"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17515847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"801","last_page":"812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9865999817848206,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8402767181396484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8085106611251831},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6670966148376465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6411604285240173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.632281482219696},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5688340663909912},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.5105301141738892},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4614381492137909},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4504868686199188},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4366699159145355},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.4223257005214691},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3208880126476288},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.15899091958999634},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.13883772492408752},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10486894845962524}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8402767181396484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8085106611251831},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6670966148376465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6411604285240173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.632281482219696},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5688340663909912},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.5105301141738892},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4614381492137909},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4504868686199188},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4366699159145355},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.4223257005214691},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3208880126476288},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.15899091958999634},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.13883772492408752},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10486894845962524},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3045300","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3045300","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09296301.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9c0f84ce2eb44de095e43fbd323b529f","is_oa":true,"landing_page_url":"https://doaj.org/article/9c0f84ce2eb44de095e43fbd323b529f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 801-812 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3045300","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3045300","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09296301.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2845204914","display_name":null,"funder_award_id":"U1811261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7457013702","display_name":null,"funder_award_id":"U181126","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3113228036.pdf","grobid_xml":"https://content.openalex.org/works/W3113228036.grobid-xml"},"referenced_works_count":97,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W779665318","https://openalex.org/W1491843047","https://openalex.org/W1511986666","https://openalex.org/W1514587017","https://openalex.org/W1600046456","https://openalex.org/W1758031947","https://openalex.org/W1771410628","https://openalex.org/W2016773334","https://openalex.org/W2053742104","https://openalex.org/W2107741520","https://openalex.org/W2115524942","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2155027007","https://openalex.org/W2165150801","https://openalex.org/W2168359464","https://openalex.org/W2173248099","https://openalex.org/W2198988526","https://openalex.org/W2251007294","https://openalex.org/W2288576358","https://openalex.org/W2398850217","https://openalex.org/W2463044753","https://openalex.org/W2547875792","https://openalex.org/W2554120691","https://openalex.org/W2747213132","https://openalex.org/W2765302304","https://openalex.org/W2772721022","https://openalex.org/W2772887568","https://openalex.org/W2788626059","https://openalex.org/W2798494119","https://openalex.org/W2799544270","https://openalex.org/W2803308811","https://openalex.org/W2889186204","https://openalex.org/W2894976951","https://openalex.org/W2898656812","https://openalex.org/W2904453761","https://openalex.org/W2946164232","https://openalex.org/W2947238749","https://openalex.org/W2947904780","https://openalex.org/W2950151997","https://openalex.org/W2950488758","https://openalex.org/W2950517718","https://openalex.org/W2953171463","https://openalex.org/W2953189830","https://openalex.org/W2953337808","https://openalex.org/W2962966033","https://openalex.org/W2963068985","https://openalex.org/W2963407617","https://openalex.org/W2963423916","https://openalex.org/W2963672698","https://openalex.org/W2963674921","https://openalex.org/W2963704132","https://openalex.org/W2963757175","https://openalex.org/W2963864421","https://openalex.org/W2964048876","https://openalex.org/W2964298957","https://openalex.org/W2968113041","https://openalex.org/W2972905192","https://openalex.org/W3011599648","https://openalex.org/W3092636900","https://openalex.org/W3099448484","https://openalex.org/W3102494930","https://openalex.org/W3102899483","https://openalex.org/W3148685027","https://openalex.org/W4214717370","https://openalex.org/W4298876402","https://openalex.org/W4299802797","https://openalex.org/W4302570325","https://openalex.org/W6630907848","https://openalex.org/W6635798015","https://openalex.org/W6638018090","https://openalex.org/W6638058698","https://openalex.org/W6676320248","https://openalex.org/W6677370284","https://openalex.org/W6683204974","https://openalex.org/W6683300800","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6687637693","https://openalex.org/W6691215711","https://openalex.org/W6712656442","https://openalex.org/W6715102896","https://openalex.org/W6725864134","https://openalex.org/W6729448088","https://openalex.org/W6738796088","https://openalex.org/W6744927671","https://openalex.org/W6746809867","https://openalex.org/W6748613090","https://openalex.org/W6749000813","https://openalex.org/W6751629939","https://openalex.org/W6755069753","https://openalex.org/W6757469721","https://openalex.org/W6761434553","https://openalex.org/W6763079203","https://openalex.org/W6763385746","https://openalex.org/W7055423279"],"related_works":["https://openalex.org/W2473373438","https://openalex.org/W2368486525","https://openalex.org/W2077224612","https://openalex.org/W2153481672","https://openalex.org/W2153238387","https://openalex.org/W4312864369","https://openalex.org/W84255947","https://openalex.org/W2014842417","https://openalex.org/W2502114474","https://openalex.org/W2061347451"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,31,52,117],"has":[2],"been":[3],"widely":[4],"applied":[5],"for":[6,41,58],"sequential":[7],"decision":[8],"making":[9],"problems":[10],"in":[11],"various":[12],"fields":[13],"of":[14,24,68,71,79,105,124],"the":[15,47,76,91,102,130],"real":[16,35,136],"world,":[17],"including":[18],"recommendation,":[19],"e-learning,":[20],"etc.":[21],"The":[22,62,122],"features":[23],"multi-policy,":[25],"latent":[26,59],"mixture":[27,60],"environments":[28],"and":[29,81,83,108,135],"offline":[30,55,115],"implied":[32],"by":[33,114,129],"many":[34],"applications":[36],"bring":[37],"a":[38,50,85],"new":[39],"challenge":[40],"reinforcement":[42,51],"learning.":[43],"To":[44],"this":[45],"challenge,":[46],"paper":[48],"proposes":[49],"approach":[53,126],"called":[54],"multi-policy":[56,86,116],"gradient":[57],"environments.":[61],"proposed":[63],"method":[64],"uses":[65],"an":[66],"objective":[67],"expected":[69],"return":[70],"trajectory":[72,80],"with":[73,118],"respect":[74],"to":[75,89],"joint":[77],"distribution":[78],"model,":[82],"adopts":[84],"searching":[87],"algorithm":[88],"find":[90],"optimal":[92],"policies":[93],"based":[94],"on":[95,132],"expectation":[96],"maximization.":[97],"We":[98],"also":[99],"prove":[100],"that":[101],"off-policy":[103],"technique":[104],"importance":[106],"sampling":[107],"advantage":[109],"function":[110],"can":[111],"be":[112],"used":[113],"fixed":[119],"historical":[120],"trajectories.":[121],"effectiveness":[123],"our":[125],"is":[127],"demonstrated":[128],"experiments":[131],"both":[133],"synthetic":[134],"datasets.":[137]},"counts_by_year":[],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}