{"id":"https://openalex.org/W2963906781","doi":"https://doi.org/10.1609/aaai.v33i01.33013404","title":"Diverse Exploration via Conjugate Policies for Policy Gradient Methods","display_name":"Diverse Exploration via Conjugate Policies for Policy Gradient Methods","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2963906781","doi":"https://doi.org/10.1609/aaai.v33i01.33013404","mag":"2963906781"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33013404","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013404","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33013404","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049167382","display_name":"Andrew Cohen","orcid":null},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Cohen","raw_affiliation_strings":["Binghamton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012574340","display_name":"Xingye Qiao","orcid":"https://orcid.org/0000-0003-0937-9822"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingye Qiao","raw_affiliation_strings":["Binghamton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736935","display_name":"Lei Yu","orcid":"https://orcid.org/0000-0002-7329-4631"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Yu","raw_affiliation_strings":["Binghamton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065504518","display_name":"Elliot Way","orcid":null},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elliot Way","raw_affiliation_strings":["Binghamton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072895530","display_name":"Xiangrong Tong","orcid":"https://orcid.org/0000-0003-4855-3723"},"institutions":[{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangrong Tong","raw_affiliation_strings":["Yantai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yantai University","institution_ids":["https://openalex.org/I18452120"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"3404","last_page":"3411"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9962000250816345,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9962000250816345,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9923999905586243,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9891999959945679,"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/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.7921603918075562},{"id":"https://openalex.org/keywords/conjugate","display_name":"Conjugate","score":0.7530624866485596},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6396538019180298},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6020042300224304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5893625617027283},{"id":"https://openalex.org/keywords/conjugate-residual-method","display_name":"Conjugate residual method","score":0.48178383708000183},{"id":"https://openalex.org/keywords/derivation-of-the-conjugate-gradient-method","display_name":"Derivation of the conjugate gradient method","score":0.4588516354560852},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3943932056427002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2617451548576355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23739373683929443},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18206465244293213}],"concepts":[{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.7921603918075562},{"id":"https://openalex.org/C197336794","wikidata":"https://www.wikidata.org/wiki/Q5161150","display_name":"Conjugate","level":2,"score":0.7530624866485596},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6396538019180298},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6020042300224304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5893625617027283},{"id":"https://openalex.org/C91394653","wikidata":"https://www.wikidata.org/wiki/Q5161159","display_name":"Conjugate residual method","level":4,"score":0.48178383708000183},{"id":"https://openalex.org/C198562538","wikidata":"https://www.wikidata.org/wiki/Q5262612","display_name":"Derivation of the conjugate gradient method","level":5,"score":0.4588516354560852},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3943932056427002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2617451548576355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23739373683929443},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18206465244293213},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33013404","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013404","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4215","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4215","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4215/4093","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33013404","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013404","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1246320210","display_name":null,"funder_award_id":"61572418","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2293436675","display_name":"TWC: Small: Collaborative: Practical Hardware-Assisted Always-On Malware Detection","funder_award_id":"1617915","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7694490589","display_name":"\u4fe1\u4efb\u7f51\u7edc\u5f62\u6210\u53ca\u5176\u5728\u667a\u80fd\u63a8\u8350\u4e2d\u7684\u5e94\u7528\u7814\u7a76","funder_award_id":"61572418","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1573082642","https://openalex.org/W1771410628","https://openalex.org/W1959608418","https://openalex.org/W2119567691","https://openalex.org/W2130801532","https://openalex.org/W2137104525","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2161966552","https://openalex.org/W2271349422","https://openalex.org/W2342662072","https://openalex.org/W2596367596","https://openalex.org/W2620671107","https://openalex.org/W2623491082","https://openalex.org/W2724169821","https://openalex.org/W2749928749","https://openalex.org/W2785967771","https://openalex.org/W2787800669","https://openalex.org/W2788729564","https://openalex.org/W2963400359","https://openalex.org/W2964337555","https://openalex.org/W3007384386","https://openalex.org/W4214717370","https://openalex.org/W4293586424","https://openalex.org/W4293775970","https://openalex.org/W4295181861","https://openalex.org/W4394666973","https://openalex.org/W6638018090","https://openalex.org/W6640963894","https://openalex.org/W6677049199","https://openalex.org/W6677916085","https://openalex.org/W6679257226","https://openalex.org/W6680108847","https://openalex.org/W6682262322","https://openalex.org/W6683153233","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6780226713","https://openalex.org/W6780559895","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W2098528027","https://openalex.org/W2388344948","https://openalex.org/W3159907817","https://openalex.org/W1503783781","https://openalex.org/W2005717169","https://openalex.org/W2350080441","https://openalex.org/W4243647929","https://openalex.org/W2279364295","https://openalex.org/W4291138086","https://openalex.org/W2316213429"],"abstract_inverted_index":{"We":[0,47],"address":[1],"the":[2,55,66],"challenge":[3],"of":[4,32,43,57,68],"effective":[5],"exploration":[6,21,71],"while":[7],"maintaining":[8],"good":[9],"performance":[10],"in":[11],"policy":[12,63,74],"gradient":[13,45],"methods.":[14],"As":[15],"a":[16,30,41],"solution,":[17],"we":[18],"propose":[19],"diverse":[20],"(DE)":[22],"via":[23],"conjugate":[24,33,44],"policies.":[25],"DE":[26,58,69],"learns":[27],"and":[28,51,65],"deploys":[29],"set":[31],"policies":[34],"which":[35],"can":[36],"be":[37],"conveniently":[38],"generated":[39],"as":[40],"byproduct":[42],"descent.":[46],"provide":[48],"both":[49],"theoretical":[50],"empirical":[52],"results":[53],"showing":[54],"effectiveness":[56],"at":[59],"achieving":[60],"exploration,":[61],"improving":[62],"performance,":[64],"advantage":[67],"over":[70],"by":[72],"random":[73],"perturbations.":[75]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}