{"id":"https://openalex.org/W3035071738","doi":"https://doi.org/10.24963/ijcai.2020/422","title":"Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent","display_name":"Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3035071738","doi":"https://doi.org/10.24963/ijcai.2020/422","mag":"3035071738"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/422","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/422","pdf_url":"https://www.ijcai.org/proceedings/2020/0422.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0422.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bowen Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bowen Weng","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huaqing Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaqing Xiong","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yingbin Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingbin Liang","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3372,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44599228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"3051","last_page":"3057"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9975000023841858,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9975000023841858,"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":0.9965000152587891,"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/T12676","display_name":"Machine Learning and ELM","score":0.9922999739646912,"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/convergence","display_name":"Convergence (economics)","score":0.6865000128746033},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.6251000165939331},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.5687000155448914},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5443000197410583},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.5443000197410583},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5209000110626221},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.501800000667572},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4138000011444092}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6865000128746033},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.6251000165939331},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5687000155448914},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.5443000197410583},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5443000197410583},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.536300003528595},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5209000110626221},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5199000239372253},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36730000376701355},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3587000072002411},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32269999384880066},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.2985999882221222},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.2741999924182892}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2020/422","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/422","pdf_url":"https://www.ijcai.org/proceedings/2020/0422.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.07422","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.07422","pdf_url":"https://arxiv.org/pdf/2007.07422","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/422","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/422","pdf_url":"https://www.ijcai.org/proceedings/2020/0422.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1194184183","display_name":"CIF: Medium: Collaborative Research: Nonconvex Optimization for High-Dimensional Signal Estimation: Theory and Fast Algorithms","funder_award_id":"1761506","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2630455048","display_name":"Management of Mobile Phone Sensing via Sparse Learning","funder_award_id":"1818904","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G663170338","display_name":"CIF: Small: Collaborative Research: Acceleration Algorithms for Large-scale Nonconvex Optimization","funder_award_id":"1909291","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G731109766","display_name":"CIF: Medium: Collaborative Research: Theory of Optimization Geometry and Algorithms for Neural Networks","funder_award_id":"1900145","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320327605","display_name":"Southern University of Science and Technology","ror":null},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035071738.pdf","grobid_xml":"https://content.openalex.org/works/W3035071738.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"convergence":[1,36,53,96],"analyses":[2],"of":[3,15,44,69,98,141],"Q-learning":[4,29,40,60,116,121],"mostly":[5],"focus":[6],"on":[7,105],"the":[8,18,52,59,77,83,91,113,119,134],"vanilla":[9,120],"stochastic":[10],"gradient":[11],"descent":[12],"(SGD)":[13],"type":[14,43],"updates.":[16,45,124],"Despite":[17],"Adaptive":[19],"Moment":[20],"Estimation":[21],"(Adam)":[22],"has":[23,32],"been":[24,34],"commonly":[25,66],"used":[26],"for":[27,39,55,71],"practical":[28],"algorithms,":[30],"there":[31],"not":[33],"any":[35],"guarantee":[37],"provided":[38],"with":[41,62,122],"such":[42],"In":[46],"this":[47],"paper,":[48],"we":[49,79],"first":[50],"characterize":[51],"rate":[54,97],"Q-AMSGrad,":[56,88],"which":[57],"is":[58,100],"algorithm":[61],"AMSGrad":[63],"update":[64],"(a":[65],"adopted":[67],"alternative":[68],"Adam":[70],"theoretical":[72],"analysis).":[73],"To":[74],"further":[75],"improve":[76],"performance,":[78],"propose":[80],"to":[81,87],"incorporate":[82],"momentum":[84],"restart":[85],"scheme":[86],"resulting":[89],"in":[90],"so-called":[92],"Q-AMSGradR":[93,99],"algorithm.":[94],"The":[95,125],"also":[101,128],"established.":[102],"Our":[103],"experiments":[104],"a":[106,139],"linear":[107],"quadratic":[108],"regulator":[109],"problem":[110],"demonstrate":[111],"that":[112],"two":[114,126],"proposed":[115],"algorithms":[117,127],"outperform":[118],"SGD":[123],"exhibit":[129],"significantly":[130],"better":[131],"performance":[132],"than":[133],"DQN":[135],"learning":[136],"method":[137],"over":[138],"batch":[140],"Atari":[142],"2600":[143],"games.":[144]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2020-06-19T00:00:00"}