{"id":"https://openalex.org/W4402351480","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651424","title":"Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features","display_name":"Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351480","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651424"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651424","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046867979","display_name":"JaeYoon Kim","orcid":"https://orcid.org/0000-0003-0898-5097"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"JaeYoon Kim","raw_affiliation_strings":["University of Technology Sydney,Australian Artificial Intelligence Institute (AAII),Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney,Australian Artificial Intelligence Institute (AAII),Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029498647","display_name":"Junyu Xuan","orcid":"https://orcid.org/0000-0002-8367-6908"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Junyu Xuan","raw_affiliation_strings":["University of Technology Sydney,Australian Artificial Intelligence Institute (AAII),Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney,Australian Artificial Intelligence Institute (AAII),Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015448106","display_name":"Christy Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christy Liang","raw_affiliation_strings":["University of Technology Sydney,Visualisation Institute,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney,Visualisation Institute,Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041615708","display_name":"Farookh Khadeer Hussain","orcid":"https://orcid.org/0000-0003-1513-8072"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Farookh Hussain","raw_affiliation_strings":["University of Technology Sydney,Australian Artificial Intelligence Institute (AAII),Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney,Australian Artificial Intelligence Institute (AAII),Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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":0.9968000054359436,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9890999794006348,"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/successor-cardinal","display_name":"Successor cardinal","score":0.7973021268844604},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.7474529147148132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6339743137359619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5535210967063904},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4969346821308136},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4371151924133301},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32630395889282227},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3224197328090668},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14832335710525513},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13537681102752686},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.07869639992713928},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07153558731079102}],"concepts":[{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.7973021268844604},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.7474529147148132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6339743137359619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5535210967063904},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4969346821308136},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4371151924133301},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32630395889282227},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3224197328090668},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14832335710525513},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13537681102752686},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.07869639992713928},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07153558731079102},{"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651424","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2015701831","https://openalex.org/W2056354534","https://openalex.org/W2440926996","https://openalex.org/W2556477470","https://openalex.org/W2742143911","https://openalex.org/W2883433335","https://openalex.org/W2913485808","https://openalex.org/W2949273680","https://openalex.org/W2951871955","https://openalex.org/W2953326529","https://openalex.org/W2963019567","https://openalex.org/W2963438456","https://openalex.org/W2963447367","https://openalex.org/W2964101952","https://openalex.org/W2983170726","https://openalex.org/W2994995984","https://openalex.org/W3214229832","https://openalex.org/W4286891004","https://openalex.org/W4287020206","https://openalex.org/W4289107543","https://openalex.org/W4289242739","https://openalex.org/W4289446378","https://openalex.org/W6616173779","https://openalex.org/W6718190810","https://openalex.org/W6730153900","https://openalex.org/W6742069676","https://openalex.org/W6748603076","https://openalex.org/W6752187413","https://openalex.org/W6753756885","https://openalex.org/W6756684005","https://openalex.org/W6756685538","https://openalex.org/W6758885689","https://openalex.org/W6764281707","https://openalex.org/W6765240361","https://openalex.org/W6791194670","https://openalex.org/W6796667233","https://openalex.org/W6800937065","https://openalex.org/W6803067813","https://openalex.org/W6841566844"],"related_works":["https://openalex.org/W2473542051","https://openalex.org/W3123320268","https://openalex.org/W2994519609","https://openalex.org/W2726593096","https://openalex.org/W2054269721","https://openalex.org/W4235459050","https://openalex.org/W2767501615","https://openalex.org/W4394050964","https://openalex.org/W4386298325","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Unsupervised":[0],"pre-training":[1,82,164],"has":[2,32],"been":[3],"on":[4,36,87,105],"the":[5,8,23,26,29,37,44,55,65,70,95,112,121,136,155,158],"lookout":[6],"for":[7,111],"virtue":[9],"of":[10,25,39,59,97,101,124,157,163],"a":[11,33,73,79,88,128,176],"value":[12],"function":[13],"representation":[14],"referred":[15],"to":[16,43,54,131],"as":[17,127],"successor":[18],"features":[19,151],"(SFs),":[20],"which":[21,107,153],"decouples":[22],"dynamics":[24],"environment":[27],"from":[28],"rewards.":[30],"It":[31],"significant":[34],"impact":[35],"process":[38],"task-specific":[40],"fine-tuning":[41],"due":[42,53],"decomposition.":[45],"However,":[46],"existing":[47],"approaches":[48],"struggle":[49],"with":[50,84,149,165,171],"local":[51],"optima":[52],"unified":[56],"intrinsic":[57],"reward":[58],"exploration":[60,90,100,161],"and":[61,69,99,138],"exploitation":[62,98],"without":[63],"considering":[64],"linear":[66],"regression":[67],"problem":[68],"discriminator":[71],"supporting":[72],"small":[74],"skill":[75],"sapce.":[76],"We":[77],"propose":[78],"novel":[80],"unsupervised":[81,147],"model":[83,143],"SFs":[85,125],"based":[86],"non-monolithic":[89],"methodology.":[91],"Our":[92,141],"approach":[93],"pursues":[94],"decomposition":[96],"an":[102],"agent":[103],"built":[104],"SFs,":[106],"requires":[108],"separate":[109],"agents":[110],"respective":[113],"purpose.":[114],"The":[115],"idea":[116],"will":[117],"leverage":[118],"not":[119],"only":[120],"inherent":[122],"characteristics":[123],"such":[126],"quick":[129],"adaptation":[130],"new":[132],"tasks":[133],"but":[134],"also":[135],"exploratory":[137],"task-agnostic":[139],"capabilities.":[140],"suggested":[142],"is":[144],"termed":[145],"Non-Monolithic":[146],"Pretraining":[148],"Successor":[150,172],"(NMPS),":[152],"improves":[154],"performance":[156],"original":[159],"monolithic":[160],"method":[162],"SFs.":[166],"NMPS":[167],"outperforms":[168],"Active":[169],"Pre-training":[170],"Features":[173],"(APS)":[174],"in":[175],"comparative":[177],"experiment.":[178]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}