{"id":"https://openalex.org/W4402822925","doi":"https://doi.org/10.1109/access.2024.3468027","title":"CAGE: A Curiosity-driven Graph-based Explore-Exploit Algorithm for Solving Deterministic Environment MDPs with Limited Episode Problem","display_name":"CAGE: A Curiosity-driven Graph-based Explore-Exploit Algorithm for Solving Deterministic Environment MDPs with Limited Episode Problem","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402822925","doi":"https://doi.org/10.1109/access.2024.3468027"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3468027","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3468027","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.1109/access.2024.3468027","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053839372","display_name":"Yide Yu","orcid":"https://orcid.org/0000-0002-5549-2925"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Yide Yu","raw_affiliation_strings":["Macao Polytechnic University, Macao, SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-5549-2925","affiliations":[{"raw_affiliation_string":"Macao Polytechnic University, Macao, SAR, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320066","display_name":"Yue Liu","orcid":"https://orcid.org/0000-0002-3292-4211"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Yue Liu","raw_affiliation_strings":["Macao Polytechnic University, Macao, SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-3292-4211","affiliations":[{"raw_affiliation_string":"Macao Polytechnic University, Macao, SAR, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059002802","display_name":"Dennis Wong","orcid":"https://orcid.org/0000-0002-6242-164X"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Dennis Wong","raw_affiliation_strings":["Macao Polytechnic University, Macao, SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University, Macao, SAR, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059208243","display_name":"Huijie Li","orcid":"https://orcid.org/0009-0003-1224-7879"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Huijie Li","raw_affiliation_strings":["Macao Polytechnic University, Macao, SAR, China"],"raw_orcid":"https://orcid.org/0009-0003-1224-7879","affiliations":[{"raw_affiliation_string":"Macao Polytechnic University, Macao, SAR, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025953461","display_name":"Jos\u00e9 Vicente Egas-L\u00f3pez","orcid":"https://orcid.org/0000-0002-5622-9192"},"institutions":[{"id":"https://openalex.org/I227486990","display_name":"University of Szeged","ror":"https://ror.org/01pnej532","country_code":"HU","type":"education","lineage":["https://openalex.org/I227486990"]},{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Vicente Egas-L\u00f3pez","raw_affiliation_strings":["University of Szeged -Artificial Intelligence Research Group, Szeged, Hungary"],"raw_orcid":"https://orcid.org/0000-0002-5622-9192","affiliations":[{"raw_affiliation_string":"University of Szeged -Artificial Intelligence Research Group, Szeged, Hungary","institution_ids":["https://openalex.org/I4210152167","https://openalex.org/I227486990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054182752","display_name":"Yan Ma","orcid":"https://orcid.org/0000-0003-4626-1401"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Ma","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16365467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/exploit","display_name":"Exploit","score":0.8605684041976929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7703104019165039},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.6081359386444092},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5213500261306763},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46492743492126465},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.45461711287498474},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4432869255542755},{"id":"https://openalex.org/keywords/algorithm-design","display_name":"Algorithm design","score":0.43509641289711},{"id":"https://openalex.org/keywords/graph-algorithms","display_name":"Graph algorithms","score":0.41919395327568054},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3293207287788391},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14799544215202332},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08118253946304321}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.8605684041976929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703104019165039},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.6081359386444092},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5213500261306763},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46492743492126465},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45461711287498474},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4432869255542755},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.43509641289711},{"id":"https://openalex.org/C2986651925","wikidata":"https://www.wikidata.org/wiki/Q1514868","display_name":"Graph algorithms","level":3,"score":0.41919395327568054},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3293207287788391},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14799544215202332},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08118253946304321},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3468027","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3468027","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6400a6f3e5de4f0a8f33620c750bf639","is_oa":true,"landing_page_url":"https://doaj.org/article/6400a6f3e5de4f0a8f33620c750bf639","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 144106-144121 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3468027","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3468027","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.6100000143051147,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W4390436776","https://openalex.org/W3016558738","https://openalex.org/W4210508727"],"abstract_inverted_index":{"The":[0,116],"explore-exploit":[1],"dilemma":[2],"in":[3,13,85,133,147],"Markov":[4],"Decision":[5],"Processes":[6],"(MDPs)":[7],"is":[8,27],"a":[9,66,112,125],"fundamental":[10],"challenge,":[11],"especially":[12],"deterministic":[14],"environments":[15],"akin":[16],"to":[17,29],"real-world":[18],"scenarios.":[19],"Balancing":[20],"exploration":[21,45,99],"and":[22,43,80,97,136],"exploitation":[23],"within":[24],"limited":[25,86],"episodes":[26],"crucial":[28],"optimize":[30],"decision-making.":[31],"Despite":[32],"existing":[33],"research,":[34],"challenges":[35],"like":[36],"parameter":[37,92],"sensitivity,":[38,93],"lack":[39],"of":[40,46,105,140],"global":[41,95],"optimality,":[42,96],"inefficient":[44],"low-value":[47],"regions":[48],"remain.":[49],"We":[50],"introduce":[51],"the":[52,103,106,121,134],"Curiosity-driven":[53],"Algorithm":[54],"based":[55],"on":[56],"Graph":[57],"for":[58,131],"Exploration":[59],"(CAGE),":[60],"which":[61],"addresses":[62],"these":[63],"issues":[64],"through":[65],"graph-based":[67],"framework.":[68],"CAGE":[69,107,122],"includes":[70],"two":[71],"variants:":[72],"CAGE-greedy,":[73],"ensuring":[74],"optimal":[75],"solutions":[76],"with":[77],"ample":[78],"episodes,":[79],"CAGE-centrality,":[81],"prioritizing":[82],"significant":[83],"states":[84],"episodes.":[87],"Key":[88],"contributions":[89],"include":[90],"eliminating":[91],"guaranteeing":[94],"enhancing":[98],"efficiency.":[100],"To":[101],"validate":[102,144],"performance":[104],"algorithm":[108,123],"series,":[109],"we":[110],"design":[111],"grid":[113],"world":[114],"experiment.":[115],"experimental":[117],"results":[118,143],"demonstrate":[119],"that":[120],"outperforms":[124],"comparative":[126],"algorithm,":[127],"indicating":[128],"its":[129,137],"feasibility":[130],"implementation":[132],"industry":[135],"high":[138],"level":[139],"explainability.":[141],"Experimental":[142],"CAGE\u2019s":[145],"effectiveness":[146],"complex":[148],"environments.":[149]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
