{"id":"https://openalex.org/W4385488590","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191833","title":"Underexplored Subspace Mining for Sparse-Reward Cooperative Multi-Agent Reinforcement Learning","display_name":"Underexplored Subspace Mining for Sparse-Reward Cooperative Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488590","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191833"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5100411381","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-5204-2929"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences","Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083652259","display_name":"Qiyue Yin","orcid":"https://orcid.org/0000-0002-3442-6275"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyue Yin","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences","Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109012644","display_name":"Junge Zhang","orcid":"https://orcid.org/0000-0002-9970-394X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junge Zhang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences","Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353673","display_name":"Hao Chen","orcid":"https://orcid.org/0009-0001-6480-7976"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028693655","display_name":"Kaiqi Huang","orcid":"https://orcid.org/0000-0002-2677-9273"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiqi Huang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences","CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, P.R.China","Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4356,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57497554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"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":0.9065999984741211,"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":0.9065999984741211,"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/subspace-topology","display_name":"Subspace topology","score":0.7989295721054077},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.787449836730957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6621731519699097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5980774760246277},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5817187428474426},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5631921291351318},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5517798662185669},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5083584189414978},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.450887531042099},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16710275411605835},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14291471242904663}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7989295721054077},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.787449836730957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6621731519699097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5980774760246277},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5817187428474426},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5631921291351318},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5517798662185669},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5083584189414978},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.450887531042099},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16710275411605835},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14291471242904663},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1482341360","https://openalex.org/W2012812921","https://openalex.org/W2140672955","https://openalex.org/W2144744117","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2769648743","https://openalex.org/W2883532348","https://openalex.org/W2914351253","https://openalex.org/W2947526499","https://openalex.org/W2949963774","https://openalex.org/W2953100042","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2964067469","https://openalex.org/W2991046523","https://openalex.org/W2996037775","https://openalex.org/W2996549507","https://openalex.org/W2998059334","https://openalex.org/W3006773485","https://openalex.org/W3039208705","https://openalex.org/W3046288222","https://openalex.org/W3134226813","https://openalex.org/W3170511602","https://openalex.org/W3209101326","https://openalex.org/W4287755265","https://openalex.org/W4288091739","https://openalex.org/W4288594419","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W6627932998","https://openalex.org/W6687681856","https://openalex.org/W6717230150","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6749304979","https://openalex.org/W6756303580","https://openalex.org/W6758641611","https://openalex.org/W6758763022","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6762973735","https://openalex.org/W6767327128","https://openalex.org/W6769462197","https://openalex.org/W6771968188","https://openalex.org/W6772005887","https://openalex.org/W6780178658","https://openalex.org/W6781750019","https://openalex.org/W6784152626","https://openalex.org/W6791533262","https://openalex.org/W6796991022"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W4319083788","https://openalex.org/W3173185086","https://openalex.org/W3103643887","https://openalex.org/W1997939726"],"abstract_inverted_index":{"Learning":[0],"cooperation":[1,165],"in":[2,14,23,88,127,154],"sparse-reward":[3,155],"multi-agent":[4],"reinforcement":[5],"learning":[6,121],"is":[7,29,37,107],"challenging,":[8],"since":[9],"agents":[10,62],"need":[11,39],"to":[12,32,40,63,77,93,97],"explore":[13,65],"the":[15,26,42,73,83,100,112,148],"large":[16],"joint-state":[17],"space":[18,45,76,135,161],"with":[19,130,158],"sparse":[20],"feedback.":[21],"However,":[22],"cooperative":[24,27,128],"games,":[25],"target":[28],"often":[30],"related":[31],"partial":[33,66],"attributes,":[34],"hence":[35],"there":[36],"no":[38],"treat":[41],"whole":[43,74],"state":[44,75,134,160],"equally.":[46],"Therefore,":[47],"we":[48,95],"propose":[49],"Underexplored":[50],"Subspace":[51],"Mining":[52],"(USM),":[53],"a":[54],"novel":[55],"type":[56],"of":[57,69,111],"intrinsic":[58],"reward":[59],"that":[60,82,139,151],"encourages":[61],"selectively":[64],"attributes":[67,85],"instead":[68],"wasting":[70],"time":[71],"on":[72,99],"accelerate":[78],"learning.":[79],"Specially,":[80],"considering":[81],"target-related":[84],"are":[86],"varying":[87],"different":[89],"games":[90,129,156],"and":[91,132,146],"hard":[92],"predefine,":[94],"choose":[96],"focus":[98],"underexplored":[101,113],"subspace":[102],"as":[103],"an":[104,108],"alternative,":[105],"which":[106],"automatic":[109],"aggregation":[110],"bottom-level":[114],"dimensions":[115],"without":[116],"any":[117],"human":[118],"design":[119],"or":[120,162],"parameters.":[122],"We":[123],"evaluate":[124],"our":[125],"method":[126,150],"discrete":[131],"continuous":[133],"separately.":[136],"Results":[137],"demonstrate":[138],"USM":[140],"consistently":[141],"outperforms":[142],"existing":[143],"state-of-the-art":[144],"methods,":[145],"becomes":[147],"only":[149],"has":[152],"succeeded":[153],"evaluated":[157],"larger":[159],"more":[163],"complicated":[164],"dynamics.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}