{"id":"https://openalex.org/W4413213152","doi":"https://doi.org/10.1109/tvt.2025.3597537","title":"Cognitive Escape Reinforcement Learning for Complex Decision Making","display_name":"Cognitive Escape Reinforcement Learning for Complex Decision Making","publication_year":2025,"publication_date":"2025-08-11","ids":{"openalex":"https://openalex.org/W4413213152","doi":"https://doi.org/10.1109/tvt.2025.3597537"},"language":"en","primary_location":{"id":"doi:10.1109/tvt.2025.3597537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2025.3597537","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"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 Vehicular Technology","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/A5039378730","display_name":"Shijin Zhao","orcid":"https://orcid.org/0009-0001-9168-1221"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijin Zhao","raw_affiliation_strings":["College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0001-9168-1221","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qihui Wu","orcid":"https://orcid.org/0000-0002-9521-5084"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihui Wu","raw_affiliation_strings":["College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9521-5084","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011900098","display_name":"Fuhui Zhou","orcid":"https://orcid.org/0000-0001-6880-6244"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuhui Zhou","raw_affiliation_strings":["College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China","College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-6880-6244","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089432787","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0003-1923-589X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1923-589X","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Huang","orcid":"https://orcid.org/0000-0002-6685-221X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Huang","raw_affiliation_strings":["College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6685-221X","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059248438","display_name":"Kai\u2010Kuang Ma","orcid":"https://orcid.org/0000-0003-2932-5709"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai-Kuang Ma","raw_affiliation_strings":["College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-2932-5709","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07816197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"75","issue":"2","first_page":"1754","last_page":"1766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12805","display_name":"Cognitive Science and Mapping","score":0.4684999883174896,"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/T12805","display_name":"Cognitive Science and Mapping","score":0.4684999883174896,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7309044599533081},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.6043763160705566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5359305739402771},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5225191116333008},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37923291325569153},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.35910993814468384},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3453325033187866},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24608898162841797},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.14339980483055115},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.12025564908981323}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7309044599533081},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.6043763160705566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5359305739402771},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5225191116333008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37923291325569153},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.35910993814468384},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3453325033187866},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24608898162841797},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.14339980483055115},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.12025564908981323}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvt.2025.3597537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2025.3597537","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"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 Vehicular Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G8431966463","display_name":null,"funder_award_id":"62222107","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2065350196","https://openalex.org/W2119000420","https://openalex.org/W2138621090","https://openalex.org/W2145339207","https://openalex.org/W2168918294","https://openalex.org/W2274405424","https://openalex.org/W2525444040","https://openalex.org/W2746553466","https://openalex.org/W2773963112","https://openalex.org/W2962887844","https://openalex.org/W2963523627","https://openalex.org/W3107153805","https://openalex.org/W3133542152","https://openalex.org/W3176588845","https://openalex.org/W3205321526","https://openalex.org/W4206251897","https://openalex.org/W4283520617","https://openalex.org/W4284890045","https://openalex.org/W4289639938","https://openalex.org/W4310705874","https://openalex.org/W4316369370","https://openalex.org/W4379739787","https://openalex.org/W4383108504","https://openalex.org/W4383212187","https://openalex.org/W4386918894","https://openalex.org/W4388837986","https://openalex.org/W4389879653","https://openalex.org/W4405516940"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3,17],"achieved":[4],"unprecedented":[5],"success":[6],"on":[7,112,121],"making":[8,113],"complex":[9,114],"decisions":[10],"encountered":[11],"in":[12,31,48,64,97],"various":[13],"applications.":[14],"However,":[15],"RL":[16,44,168],"two":[18,74],"well-recognized":[19],"technical":[20],"challenges,":[21],"namely,weak":[22],"scene":[23],"generalizationandlocal-optima":[24],"trapping;":[25],"both":[26],"lead":[27],"to":[28,85,135,173],"degraded":[29],"performance":[30],"terms":[32],"of":[33,73,133,150,165],"navigation":[34,142],"accuracy":[35],"and":[36,80,93,153],"efficiency.":[37],"To":[38],"tackle":[39],"these":[40],"issues,":[41],"a":[42],"novel":[43],"framework":[45,71],"is":[46,57,119,130],"proposed":[47,167],"this":[49],"paper,":[50],"called":[51],"thecognitive":[52,81],"escape":[53,82],"reinforcement":[54],"learning(CERL),":[55],"which":[56],"inspired":[58],"by":[59,89],"the":[60,65,86,90,94,106,110,122,127,140,148,163,174],"cognition":[61,78],"ability":[62],"inherited":[63],"human":[66],"beings.":[67],"Our":[68,116],"developed":[69,117],"CERL":[70],"consists":[72],"sequential":[75],"stages:":[76],"thesemantic":[77],"module(SCM)":[79],"module(CEM),":[83],"corresponding":[84],"roles":[87],"played":[88],"perception":[91],"layer":[92,96],"decision":[95],"traditional":[98],"RL,":[99],"respectively.":[100],"The":[101,144],"SCM":[102,118],"exploitssemanticinformation":[103],"extracted":[104,125],"from":[105,126,155],"scenes":[107,128],"for":[108,138],"facilitating":[109],"CEM":[111,145],"decisions.":[115],"based":[120],"semantic":[123],"information":[124],"that":[129],"quite":[131],"capable":[132],"adapting":[134],"new":[136],"environments":[137],"improving":[139],"agent's":[141],"performance.":[143],"proactively":[146],"identifies":[147],"occurrences":[149],"local-optima":[151],"trappings":[152],"escapes":[154],"such":[156],"incidences":[157],"responsively.":[158],"Extensive":[159],"experiments":[160],"have":[161],"demonstrated":[162],"superiority":[164],"our":[166],"method,":[169],"CERL,":[170],"when":[171],"compared":[172],"state-of-the-art":[175],"methods.":[176]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
