{"id":"https://openalex.org/W4401863542","doi":"https://doi.org/10.1145/3637528.3671750","title":"Maximum-Entropy Regularized Decision Transformer with Reward Relabelling for Dynamic Recommendation","display_name":"Maximum-Entropy Regularized Decision Transformer with Reward Relabelling for Dynamic Recommendation","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863542","doi":"https://doi.org/10.1145/3637528.3671750"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671750","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671750","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3637528.3671750","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057487706","display_name":"Xiaocong Chen","orcid":"https://orcid.org/0000-0002-8849-4943"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaocong Chen","raw_affiliation_strings":["Data 61, CSIRO, Eveleigh, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8849-4943","affiliations":[{"raw_affiliation_string":"Data 61, CSIRO, Eveleigh, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358930","display_name":"Siyu Wang","orcid":"https://orcid.org/0009-0008-8726-5277"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Siyu Wang","raw_affiliation_strings":["The University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0008-8726-5277","affiliations":[{"raw_affiliation_string":"The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["Data 61, CSIRO & The University of New South Wales, Eveleigh, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4149-839X","affiliations":[{"raw_affiliation_string":"Data 61, CSIRO & The University of New South Wales, Eveleigh, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I31746571","https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4496,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.95597127,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"376","last_page":"384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9987000226974487,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.6371213793754578},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5374178886413574},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.43783360719680786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4223899245262146},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10804235935211182},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09704884886741638},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07078984379768372},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06422120332717896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6371213793754578},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5374178886413574},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.43783360719680786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4223899245262146},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10804235935211182},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09704884886741638},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07078984379768372},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06422120332717896},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671750","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671750","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3637528.3671750","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671750","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2155912844","https://openalex.org/W2562337727","https://openalex.org/W2787933113","https://openalex.org/W2799544270","https://openalex.org/W2893359107","https://openalex.org/W2963440040","https://openalex.org/W2963654596","https://openalex.org/W2964108915","https://openalex.org/W3017289192","https://openalex.org/W3033324992","https://openalex.org/W3102899483","https://openalex.org/W3200235377","https://openalex.org/W3208231292","https://openalex.org/W4212774754","https://openalex.org/W4284712454","https://openalex.org/W4292419518","https://openalex.org/W4318159260","https://openalex.org/W4324312897","https://openalex.org/W4384891727","https://openalex.org/W6600007113","https://openalex.org/W6600018615"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Reinforcement":[0],"learning-based":[1],"recommender":[2],"systems":[3],"have":[4,37,175],"recently":[5],"gained":[6],"popularity.":[7],"However,":[8],"due":[9],"to":[10,128,141,150,155],"the":[11,22,57,63,129,152,168],"typical":[12],"limitations":[13],"of":[14,21,54,91,131,172],"simulation":[15],"environments":[16],"(e.g.,":[17],"data":[18],"inefficiency),":[19],"most":[20],"work":[23],"cannot":[24],"be":[25],"broadly":[26],"applied":[27],"in":[28,72,84,97,146,185],"all":[29],"domains.":[30],"To":[31,166],"counter":[32],"these":[33],"challenges,":[34],"recent":[35],"advancements":[36],"leveraged":[38],"offline":[39,49,182],"reinforcement":[40],"learning":[41],"methods,":[42],"notable":[43],"for":[44,115],"their":[45],"data-driven":[46],"approach":[47,66,120],"utilizing":[48],"datasets.":[50],"A":[51],"prominent":[52],"example":[53],"this":[55],"is":[56,139],"Decision":[58,64,86,110],"Transformer.":[59],"Despite":[60],"its":[61],"popularity,":[62],"Transformer":[65,111],"has":[67],"inherent":[68],"drawbacks,":[69],"particularly":[70],"evident":[71],"recommendation":[73],"methods":[74],"based":[75],"on":[76],"it.":[77],"This":[78,137],"paper":[79],"identifies":[80],"two":[81],"key":[82],"shortcomings":[83],"existing":[85],"Transformer-based":[87],"methods:":[88],"a":[89,104,123,132,161],"lack":[90],"stitching":[92],"capability":[93,154],"and":[94,170,184],"limited":[95],"effectiveness":[96,169],"online":[98,147,187],"adoption.":[99],"In":[100],"response,":[101],"we":[102,159,174],"introduce":[103],"novel":[105],"methodology":[106],"named":[107],"Max-Entropy":[108],"enhanced":[109,134],"with":[112,122],"Reward":[113],"Relabeling":[114],"Offline":[116],"RLRS":[117],"(EDT4Rec).":[118],"Our":[119],"begins":[121],"max":[124],"entropy":[125],"perspective,":[126],"leading":[127],"development":[130],"max-entropy":[133],"exploration":[135,145],"strategy.":[136],"strategy":[138],"designed":[140],"facilitate":[142],"more":[143],"effective":[144],"environments.":[148],"Additionally,":[149],"augment":[151],"model's":[153],"stitch":[156],"sub-optimal":[157],"trajectories,":[158],"incorporate":[160],"unique":[162],"reward":[163],"relabeling":[164],"technique.":[165],"validate":[167],"superiority":[171],"EDT4Rec,":[173],"conducted":[176],"comprehensive":[177],"experiments":[178],"across":[179],"six":[180],"real-world":[181],"datasets":[183],"an":[186],"simulator.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}