{"id":"https://openalex.org/W4413156553","doi":"https://doi.org/10.1109/tetci.2025.3595684","title":"Contrastive Learning-Based Agent Modeling for Deep Reinforcement Learning","display_name":"Contrastive Learning-Based Agent Modeling for Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-08-13","ids":{"openalex":"https://openalex.org/W4413156553","doi":"https://doi.org/10.1109/tetci.2025.3595684"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2025.3595684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2025.3595684","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","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/A5086940360","display_name":"Wenhao Ma","orcid":"https://orcid.org/0000-0003-2350-4597"},"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":"Wenhao Ma","raw_affiliation_strings":["Australian AI Institute, School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-2350-4597","affiliations":[{"raw_affiliation_string":"Australian AI Institute, School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076932590","display_name":"Yu\u2010Cheng Chang","orcid":"https://orcid.org/0000-0001-9244-0318"},"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":"Yu-Chen Chang","raw_affiliation_strings":["Australian AI Institute, School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9244-0318","affiliations":[{"raw_affiliation_string":"Australian AI Institute, School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101750857","display_name":"Jie Yang","orcid":"https://orcid.org/0000-0002-3109-472X"},"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":"Jie Yang","raw_affiliation_strings":["Australian AI Institute, School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3109-472X","affiliations":[{"raw_affiliation_string":"Australian AI Institute, School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100773301","display_name":"Yu\u2013Kai Wang","orcid":"https://orcid.org/0000-0001-8390-2664"},"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":"Yu-Kai Wang","raw_affiliation_strings":["Australian AI Institute, School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8390-2664","affiliations":[{"raw_affiliation_string":"Australian AI Institute, School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058936239","display_name":"Chin\u2010Teng Lin","orcid":"https://orcid.org/0000-0001-8371-8197"},"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":"Chin-Teng Lin","raw_affiliation_strings":["Australian AI Institute, School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8371-8197","affiliations":[{"raw_affiliation_string":"Australian AI Institute, School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, 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":5.1313,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95166141,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"9","issue":"5","first_page":"3719","last_page":"3726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5947999954223633,"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":0.5947999954223633,"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":0.6360538005828857},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5503430366516113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5035941004753113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41575199365615845},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2764350473880768},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08525523543357849}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6360538005828857},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5503430366516113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5035941004753113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41575199365615845},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2764350473880768},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08525523543357849}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2025.3595684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2025.3595684","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1287172568","display_name":"AI-Human Empowered Team Decision-Making","funder_award_id":"DP220100803","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G4880096179","display_name":"Mind-reading AI to translate silent speech into words","funder_award_id":"DP250103612","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G5669425141","display_name":null,"funder_award_id":"DINPP2019 S1-03/09","funder_id":"https://openalex.org/F4320331403","funder_display_name":"NSW Defence Innovation Network"}],"funders":[{"id":"https://openalex.org/F4320331403","display_name":"NSW Defence Innovation Network","ror":null},{"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":13,"referenced_works":["https://openalex.org/W2156194062","https://openalex.org/W2567455162","https://openalex.org/W2602275733","https://openalex.org/W2758442112","https://openalex.org/W3035524453","https://openalex.org/W3093210455","https://openalex.org/W3093840653","https://openalex.org/W3114632476","https://openalex.org/W4252279978","https://openalex.org/W4313019631","https://openalex.org/W4382202823","https://openalex.org/W4385245566","https://openalex.org/W4390446540"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Multi-agent":[0],"systems":[1],"often":[2],"require":[3],"agents":[4,12,30,90],"to":[5,63],"collaborate":[6],"with":[7,13],"or":[8,17,93],"compete":[9],"against":[10],"other":[11,47],"diverse":[14],"goals,":[15],"behaviors,":[16],"strategies.":[18],"Agent":[19],"modeling":[20,79,109],"is":[21,36,71,149],"essential":[22],"when":[23],"designing":[24],"adaptive":[25,68],"policies":[26],"for":[27,98],"intelligent":[28],"machine":[29],"in":[31,157,174],"multi-agent":[32,179],"systems,":[33],"as":[34],"this":[35],"the":[37,41,65,83,134,138,162,169,203],"means":[38],"by":[39,73,192],"which":[40,70,201],"controlled":[42],"agent":[43,78,108,140],"(ego":[44],"agent)":[45],"understands":[46],"agents'":[48],"(modeled":[49],"agents)":[50],"behavior":[51],"and":[52,106,143,177,198],"extracts":[53],"their":[54],"meaningful":[55],"policy":[56,69,99,155],"representations.":[57],"These":[58],"representations":[59,156],"can":[60],"be":[61],"used":[62],"enhance":[64],"ego":[66,139],"agent's":[67],"trained":[72],"reinforcement":[74,189],"learning.":[75],"However,":[76],"existing":[77],"approaches":[80],"typically":[81],"assume":[82],"availability":[84],"of":[85,151,164,171],"local":[86,135],"observations":[87,136],"from":[88,137,161],"modeled":[89],"during":[91,141],"training":[92,142],"a":[94,113],"long":[95],"observation":[96],"trajectory":[97],"adaption.":[100],"To":[101],"remove":[102],"these":[103,146],"constrictive":[104],"assumptions":[105],"improve":[107],"performance,":[110],"we":[111],"devised":[112],"<bold":[114,117,120,123],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[115,118,121,124,127],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">C</b>ontrastive":[116],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">L</b>earning-based":[119],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">A</b>gent":[122],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</b>odeling":[125],"(<bold":[126],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">CLAM</b>)":[128],"method":[129],"that":[130,185],"relies":[131],"only":[132],"on":[133,196],"execution.":[144],"With":[145],"observations,":[147],"CLAM":[148],"capable":[150],"generating":[152],"consistent":[153],"high-quality":[154],"real":[158],"time":[159],"right":[160],"beginning":[163],"each":[165],"episode.":[166],"We":[167],"evaluated":[168],"efficacy":[170],"our":[172,186],"approach":[173,187],"both":[175],"cooperative":[176,197],"competitive":[178,199],"environments.":[180],"The":[181],"experiment":[182],"results":[183],"demonstrate":[184],"improves":[188],"learning":[190],"performance":[191],"at":[193],"least":[194],"28%":[195],"tasks,":[200],"exceeds":[202],"state-of-the-art.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}