{"id":"https://openalex.org/W3035064526","doi":"https://doi.org/10.24963/ijcai.2020/276","title":"Reinforcement Learning with Dynamic Boltzmann Softmax Updates","display_name":"Reinforcement Learning with Dynamic Boltzmann Softmax Updates","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3035064526","doi":"https://doi.org/10.24963/ijcai.2020/276","mag":"3035064526"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/276","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/276","pdf_url":"https://www.ijcai.org/proceedings/2020/0276.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":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0276.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090888372","display_name":"Ling Pan","orcid":"https://orcid.org/0000-0002-4413-281X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ling Pan","raw_affiliation_strings":["IIIS, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"IIIS, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016589992","display_name":"Qingpeng Cai","orcid":"https://orcid.org/0000-0001-6451-9299"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingpeng Cai","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101704281","display_name":"Qi Meng","orcid":"https://orcid.org/0000-0001-7082-6666"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qi Meng","raw_affiliation_strings":["Microsoft","Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344294","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0001-5090-9915"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Microsoft","Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082905458","display_name":"Longbo Huang","orcid":"https://orcid.org/0000-0002-7341-447X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbo Huang","raw_affiliation_strings":["IIIS, Tsinghua Univeristy","IIIS, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"IIIS, Tsinghua Univeristy","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"IIIS, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090888372"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.5825,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.91655015,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1992","last_page":"1998"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9857000112533569,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.9738603830337524},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8028345108032227},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.724830150604248},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6585472822189331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6449463367462158},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5253711938858032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5143007636070251},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.506650984287262},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49733927845954895},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4666473865509033},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.45102187991142273},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2462751269340515},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.19464793801307678},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06612196564674377}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9738603830337524},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8028345108032227},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.724830150604248},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6585472822189331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6449463367462158},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5253711938858032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5143007636070251},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.506650984287262},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49733927845954895},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4666473865509033},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.45102187991142273},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2462751269340515},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.19464793801307678},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06612196564674377},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/276","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/276","pdf_url":"https://www.ijcai.org/proceedings/2020/0276.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"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/276","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/276","pdf_url":"https://www.ijcai.org/proceedings/2020/0276.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":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7300000190734863}],"awards":[{"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/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/G5939423041","display_name":null,"funder_award_id":"Technology","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/G72957147","display_name":null,"funder_award_id":"61672316","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035064526.pdf","grobid_xml":"https://content.openalex.org/works/W3035064526.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1626977535","https://openalex.org/W1977655452","https://openalex.org/W2107726111","https://openalex.org/W2119076496","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2153925537","https://openalex.org/W2155968351","https://openalex.org/W2201467212","https://openalex.org/W2554120691","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2803767077","https://openalex.org/W2806985155","https://openalex.org/W2907537824","https://openalex.org/W2945159000","https://openalex.org/W2949561945","https://openalex.org/W2949996623","https://openalex.org/W2951799221","https://openalex.org/W2962847657","https://openalex.org/W2963267001","https://openalex.org/W2965916140","https://openalex.org/W2985337500","https://openalex.org/W3011120880","https://openalex.org/W3103780890","https://openalex.org/W4293871015","https://openalex.org/W4300491190","https://openalex.org/W6739455066","https://openalex.org/W6838887796","https://openalex.org/W6864014924"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W3090555870","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Value":[0],"function":[1,55],"estimation":[2,85],"is":[3,16],"an":[4],"important":[5],"task":[6],"in":[7,43,67,114],"reinforcement":[8],"learning,":[9],"i.e.,":[10],"prediction.":[11],"The":[12],"Boltzmann":[13,58],"softmax":[14,59,97],"operator":[15,82],"a":[17],"natural":[18],"value":[19,44,54,88],"estimator":[20],"and":[21,34,72],"can":[22],"provide":[23],"several":[24],"benefits.":[25],"However,":[26],"it":[27],"does":[28],"not":[29],"satisfy":[30],"the":[31,53,68,80,87,92,96,102,107],"non-expansion":[32],"property,":[33],"its":[35],"direct":[36],"use":[37],"may":[38],"fail":[39],"to":[40,51],"converge":[41],"even":[42],"iteration.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,100],"propose":[50,101],"update":[52],"with":[56],"dynamic":[57],"(DBS)":[60],"operator,":[61,109],"which":[62,90,110],"has":[63],"good":[64],"convergence":[65,93],"property":[66],"setting":[69],"of":[70,86,95,117],"planning":[71],"learning.":[73],"Experimental":[74],"results":[75],"on":[76],"GridWorld":[77],"show":[78],"that":[79],"DBS":[81,108],"enables":[83],"better":[84],"function,":[89],"rectifies":[91],"issue":[94],"operator.":[98],"Finally,":[99],"DBS-DQN":[103],"algorithm":[104],"by":[105],"applying":[106],"outperforms":[111],"DQN":[112],"substantially":[113],"40":[115],"out":[116],"49":[118],"Atari":[119],"games.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}