{"id":"https://openalex.org/W4385756491","doi":"https://doi.org/10.1109/tg.2023.3304315","title":"Multigoal Reinforcement Learning via Exploring Entropy-Regularized Successor Matching","display_name":"Multigoal Reinforcement Learning via Exploring Entropy-Regularized Successor Matching","publication_year":2023,"publication_date":"2023-08-11","ids":{"openalex":"https://openalex.org/W4385756491","doi":"https://doi.org/10.1109/tg.2023.3304315"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2023.3304315","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tg.2023.3304315","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"},"type":"article","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/A5039711250","display_name":"Xiaoyun Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyun Feng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4131-0625","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101550975","display_name":"Yun Zhou","orcid":"https://orcid.org/0000-0002-7466-4593"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Zhou","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University, Hefei, China","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7466-4593","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09432721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"4","first_page":"538","last_page":"548"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9703999757766724,"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":0.9703999757766724,"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/successor-cardinal","display_name":"Successor cardinal","score":0.9425768852233887},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6108677387237549},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5923658609390259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47494104504585266},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4642525315284729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4068412780761719},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35175609588623047},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.15012136101722717}],"concepts":[{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.9425768852233887},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6108677387237549},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5923658609390259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47494104504585266},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4642525315284729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4068412780761719},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35175609588623047},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.15012136101722717},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2023.3304315","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tg.2023.3304315","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6275478984","display_name":null,"funder_award_id":"62102387","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":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1517411378","https://openalex.org/W1993411524","https://openalex.org/W2056354534","https://openalex.org/W2145339207","https://openalex.org/W2165698076","https://openalex.org/W2736601468","https://openalex.org/W2761873684","https://openalex.org/W2897007337","https://openalex.org/W2963019567","https://openalex.org/W2963099939","https://openalex.org/W2963447367","https://openalex.org/W2995579991","https://openalex.org/W4286857134","https://openalex.org/W4293872189","https://openalex.org/W4296512964","https://openalex.org/W4297804343","https://openalex.org/W6616173779","https://openalex.org/W6631015714","https://openalex.org/W6632504492","https://openalex.org/W6635701881","https://openalex.org/W6684921986","https://openalex.org/W6716653466","https://openalex.org/W6718190810","https://openalex.org/W6734517396","https://openalex.org/W6737937804","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6743660412","https://openalex.org/W6745277162","https://openalex.org/W6747473740","https://openalex.org/W6748012927","https://openalex.org/W6748599296","https://openalex.org/W6748603076","https://openalex.org/W6752089545","https://openalex.org/W6752187413","https://openalex.org/W6753060773","https://openalex.org/W6755355703","https://openalex.org/W6756287877","https://openalex.org/W6756684005","https://openalex.org/W6757058172","https://openalex.org/W6760405395","https://openalex.org/W6760560886","https://openalex.org/W6762640273","https://openalex.org/W6763356705","https://openalex.org/W6765407481","https://openalex.org/W6768220214","https://openalex.org/W6769035977","https://openalex.org/W6771440238","https://openalex.org/W6779780899","https://openalex.org/W6780559895","https://openalex.org/W6791623595","https://openalex.org/W6797805403","https://openalex.org/W6803455561"],"related_works":["https://openalex.org/W3123320268","https://openalex.org/W2473542051","https://openalex.org/W2994519609","https://openalex.org/W2726593096","https://openalex.org/W2054269721","https://openalex.org/W4214635639","https://openalex.org/W2390822611","https://openalex.org/W2084522819","https://openalex.org/W2767501615","https://openalex.org/W3166948032"],"abstract_inverted_index":{"Multigoal":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"algorithms":[4],"tend":[5],"to":[6,20,33,99,122,134],"achieve":[7],"and":[8,75,96,169],"generalize":[9],"over":[10],"diverse":[11],"goals.":[12],"However,":[13],"unlike":[14],"single-goal":[15],"agents,":[16,52],"multigoal":[17,51,63],"agents":[18],"struggle":[19],"break":[21],"through":[22],"the":[23,66,70,90,149,189],"exploration":[24,64,150],"bottleneck":[25],"with":[26,38,127,166],"a":[27,93,107],"fair":[28],"share":[29],"of":[30,68,72,92,118,139,172],"interactions,":[31],"owing":[32],"rarely":[34],"reusable":[35],"goal-oriented":[36],"experiences":[37],"sparse":[39,113,167],"goal-reaching":[40,101,186],"rewards.":[41,114],"Therefore,":[42],"well-arranged":[43],"behavior":[44,128,182],"goals":[45,129,183],"during":[46],"training":[47],"are":[48,131],"essential":[49],"for":[50],"especially":[53],"in":[54,137,147,170],"long-horizon":[55,155],"tasks.":[56],"To":[57],"this":[58],"end,":[59],"we":[60],"propose":[61],"efficient":[62],"on":[65,153],"basis":[67],"maximizing":[69],"entropy":[71],"successor":[73,78,94,102,190],"features":[74],"Exploring":[76],"entropy-regularized":[77,100],"matching,":[79],"namely,":[80],"E<inline-formula":[81,85,160,175],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[82,86,161,176],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[83,87,162,177],"notation=\"LaTeX\">$^{2}$</tex-math></inline-formula>SM.":[84],"notation=\"LaTeX\">$^{2}$</tex-math></inline-formula>SM":[88,163,178],"adopts":[89],"idea":[91],"feature":[95,111],"extends":[97],"it":[98],"mapping":[103],"that":[104,130,159],"serves":[105],"as":[106,143,145],"more":[108,132],"stable":[109],"state":[110,141],"under":[112],"The":[115],"key":[116],"contribution":[117],"our":[119],"work":[120],"is":[121],"perform":[123],"intrinsic":[124],"goal":[125],"setting":[126],"likely":[133],"be":[135],"achieved":[136],"terms":[138],"future":[140],"occupancies":[142],"well":[144,165],"promising":[146],"expanding":[148],"frontier.":[151],"Experiments":[152],"challenging":[154],"manipulation":[156],"tasks":[157],"show":[158],"deals":[164],"rewards":[168],"pursuit":[171],"maximal":[173],"state-covering,":[174],"efficiently":[179],"identifies":[180],"valuable":[181],"toward":[184],"specific":[185],"by":[187],"matching":[188],"mapping.":[191]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}