{"id":"https://openalex.org/W4385768110","doi":"https://doi.org/10.24963/ijcai.2023/522","title":"Towards Long-delayed Sparsity: Learning a Better Transformer through Reward Redistribution","display_name":"Towards Long-delayed Sparsity: Learning a Better Transformer through Reward Redistribution","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385768110","doi":"https://doi.org/10.24963/ijcai.2023/522"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/522","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/522","pdf_url":"https://www.ijcai.org/proceedings/2023/0522.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0522.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024079569","display_name":"Tianchen Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianchen Zhu","raw_affiliation_strings":["Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University","School of Computer Science and Engineering, Beihang University","Shenyuan Honors College, Beihang University"],"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Shenyuan Honors College, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101954312","display_name":"Yue Qiu","orcid":"https://orcid.org/0000-0002-2073-332X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Qiu","raw_affiliation_strings":["Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University","School of Computer Science and Engineering, Beihang University"],"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086419494","display_name":"Haoyi Zhou","orcid":"https://orcid.org/0000-0002-2393-3634"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyi Zhou","raw_affiliation_strings":["Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University","School of Software, Beihang University"],"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Software, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100380463","display_name":"Jianxin Li","orcid":"https://orcid.org/0000-0001-5152-0055"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxin Li","raw_affiliation_strings":["Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University","School of Computer Science and Engineering, Beihang University"],"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024079569"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.5147,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71397161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4693","last_page":"4701"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9902999997138977,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9858999848365784,"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":0.7718876600265503},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7609080076217651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5270200967788696},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5051143765449524},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.465142160654068},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44781094789505005},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4344451427459717},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42754819989204407},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19059908390045166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11237025260925293},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11091658473014832},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.07711207866668701}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7718876600265503},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609080076217651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5270200967788696},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5051143765449524},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.465142160654068},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44781094789505005},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4344451427459717},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42754819989204407},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19059908390045166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11237025260925293},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11091658473014832},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.07711207866668701},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/522","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/522","pdf_url":"https://www.ijcai.org/proceedings/2023/0522.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/522","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/522","pdf_url":"https://www.ijcai.org/proceedings/2023/0522.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","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/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/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4966747191","display_name":null,"funder_award_id":"62202029","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/G8128231151","display_name":null,"funder_award_id":"62225202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8513333314","display_name":null,"funder_award_id":"2021ZD01","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"},{"id":"https://openalex.org/F4320321125","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56"},{"id":"https://openalex.org/F4320329053","display_name":"Beijing Advanced Innovation Center for Big Data and Brain Computing","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385768110.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W1924770834","https://openalex.org/W2095564494","https://openalex.org/W2115008305","https://openalex.org/W2124169341","https://openalex.org/W2163602945","https://openalex.org/W2198041288","https://openalex.org/W2404342324","https://openalex.org/W2604763608","https://openalex.org/W2751516180","https://openalex.org/W2803767077","https://openalex.org/W2809013025","https://openalex.org/W2896457183","https://openalex.org/W2902982219","https://openalex.org/W2947137205","https://openalex.org/W2949248709","https://openalex.org/W2951104886","https://openalex.org/W2962787969","https://openalex.org/W2962802272","https://openalex.org/W2963277051","https://openalex.org/W2963864421","https://openalex.org/W2964096423","https://openalex.org/W2965908679","https://openalex.org/W3016525976","https://openalex.org/W3017367030","https://openalex.org/W3034769194","https://openalex.org/W3041202696","https://openalex.org/W3094502228","https://openalex.org/W3095669803","https://openalex.org/W3100081294","https://openalex.org/W3169291081","https://openalex.org/W3174718176","https://openalex.org/W3177318507","https://openalex.org/W4214717370","https://openalex.org/W4225623725","https://openalex.org/W4226325719","https://openalex.org/W4283817199","https://openalex.org/W4287126489","https://openalex.org/W4287997992","https://openalex.org/W4287998029","https://openalex.org/W4287998216","https://openalex.org/W4307225071","https://openalex.org/W4315489353","https://openalex.org/W4382240280","https://openalex.org/W4385245566","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W4255576661","https://openalex.org/W1516574938","https://openalex.org/W2625725254","https://openalex.org/W2563912921"],"abstract_inverted_index":{"Recently,":[0],"Decision":[1],"Transformer":[2],"(DT)":[3],"pioneered":[4],"the":[5,36,41,50,97,105,111,125],"offline":[6],"RL":[7],"into":[8],"a":[9,32,46,84,115],"contextual":[10],"conditional":[11],"sequence":[12],"modeling":[13],"paradigm,":[14],"which":[15],"leverages":[16],"self-attended":[17],"autoregression":[18],"to":[19],"learn":[20],"from":[21],"global":[22,65,120],"target":[23],"rewards,":[24],"states,":[25],"and":[26,94,131],"actions.":[27],"However,":[28],"many":[29],"applications":[30],"have":[31],"severe":[33],"delay":[34,56],"of":[35,52],"above":[37],"signals,":[38],"such":[39],"as":[40,114],"agent":[42],"can":[43],"only":[44],"obtain":[45],"reward":[47,86,92,99],"signal":[48],"at":[49],"end":[51],"each":[53,101],"trajectory.":[54],"This":[55],"causes":[57],"an":[58,133],"unwanted":[59],"bias":[60],"cumulating":[61],"in":[62],"autoregressive":[63],"learning":[64,78,90],"signals.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,109],"focused":[71],"its":[72],"virtual":[73],"example":[74],"on":[75,128],"episodic":[76],"reinforcement":[77],"with":[79],"trajectory":[80],"feedback.":[81],"We":[82,122],"propose":[83],"new":[85],"redistribution":[87],"algorithm":[88],"for":[89,119],"parameterized":[91],"functions,":[93],"it":[95],"decomposes":[96],"long-delayed":[98,138],"onto":[100],"timestep.":[102],"To":[103],"improve":[104],"redistributing's":[106],"adaptation":[107],"ability,":[108],"formulate":[110],"previous":[112],"decomposition":[113],"bi-level":[116],"optimization":[117],"problem":[118],"optimal.":[121],"extensively":[123],"evaluate":[124],"proposed":[126],"method":[127],"various":[129],"benchmarks":[130],"demonstrate":[132],"overwhelming":[134],"performance":[135],"improvement":[136],"under":[137],"settings.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}