{"id":"https://openalex.org/W4414272467","doi":"https://doi.org/10.1109/ichms65439.2025.11154198","title":"A Trust-Aware Reinforcement Learning Approach to Enhance Human-Agent Teaming: An Overcooked-AI Study","display_name":"A Trust-Aware Reinforcement Learning Approach to Enhance Human-Agent Teaming: An Overcooked-AI Study","publication_year":2025,"publication_date":"2025-05-26","ids":{"openalex":"https://openalex.org/W4414272467","doi":"https://doi.org/10.1109/ichms65439.2025.11154198"},"language":"en","primary_location":{"id":"doi:10.1109/ichms65439.2025.11154198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichms65439.2025.11154198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 5th International Conference on Human-Machine Systems (ICHMS)","raw_type":"proceedings-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/A5081841950","display_name":"Kiana Jafari Meimandi","orcid":"https://orcid.org/0000-0002-2001-3488"},"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"]},{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]},{"id":"https://openalex.org/I13805885","display_name":"Vaughn College of Aeronautics and Technology","ror":"https://ror.org/056e22e24","country_code":"US","type":"education","lineage":["https://openalex.org/I13805885"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Kiana Jafari Meimandi","raw_affiliation_strings":["Stanford University,Aeronautics and Astronautics Department,California,USA"],"affiliations":[{"raw_affiliation_string":"Stanford University,Aeronautics and Astronautics Department,California,USA","institution_ids":["https://openalex.org/I46020346","https://openalex.org/I9842412","https://openalex.org/I13805885"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041183239","display_name":"Matthew L. Bolton","orcid":"https://orcid.org/0000-0002-7943-0497"},"institutions":[{"id":"https://openalex.org/I4210116219","display_name":"Engineering Systems (United States)","ror":"https://ror.org/02qg60849","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew L. Bolton","raw_affiliation_strings":["University of Virginia,Systems and Information Engineering,Virginia,USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia,Systems and Information Engineering,Virginia,USA","institution_ids":["https://openalex.org/I4210116219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056670558","display_name":"Peter A. Beling","orcid":"https://orcid.org/0000-0003-2196-6982"},"institutions":[{"id":"https://openalex.org/I1329048335","display_name":"National Institute of Aerospace","ror":"https://ror.org/00fadxs59","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1329048335"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter A. Beling","raw_affiliation_strings":["National Security Institute, Virginia Tech,Virginia,USA"],"affiliations":[{"raw_affiliation_string":"National Security Institute, Virginia Tech,Virginia,USA","institution_ids":["https://openalex.org/I1329048335"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081841950"],"corresponding_institution_ids":["https://openalex.org/I13805885","https://openalex.org/I46020346","https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":2.3289,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89655625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.8185999989509583,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.8185999989509583,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7081999778747559,"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":0.855400025844574},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.6481999754905701},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.520799994468689},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.48989999294281006},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4668999910354614},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.42289999127388}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.855400025844574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715499997138977},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.6481999754905701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317999720573425},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4016999900341034},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.27559998631477356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ichms65439.2025.11154198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichms65439.2025.11154198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 5th International Conference on Human-Machine Systems (ICHMS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310536","display_name":"University of Virginia","ror":"https://ror.org/0153tk833"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W2174803659","https://openalex.org/W2796290181","https://openalex.org/W2964132611","https://openalex.org/W3013998503","https://openalex.org/W3212787721","https://openalex.org/W4220962114","https://openalex.org/W4300803006","https://openalex.org/W4308516699","https://openalex.org/W4308609119","https://openalex.org/W4312309366","https://openalex.org/W4388521754","https://openalex.org/W4403918690"],"related_works":[],"abstract_inverted_index":{"This":[0,111,146,168],"study":[1],"integrates":[2],"a":[3,10,70,108,143,171],"previously":[4],"developed":[5],"trust":[6,20,38,58,83,106,123,163],"prediction":[7,21],"model":[8,45],"into":[9,165],"reinforcement":[11],"learning":[12],"framework":[13],"to":[14,35,55,85,101,116],"enhance":[15],"human-agent":[16],"collaboration.":[17],"The":[18,95],"ensemble":[19],"model,":[22],"consisting":[23],"of":[24,105,161],"long":[25],"short-term":[26],"memory":[27],"and":[28,64,89,124,177],"neural":[29],"network":[30],"architectures,":[31],"analyzes":[32],"gameplay":[33],"trajectories":[34],"predict":[36],"dynamic":[37],"levels":[39],"in":[40,80,153,181],"real-time.":[41],"We":[42],"embed":[43],"this":[44],"within":[46,126],"the":[47,51,81,103,119,159],"Overcooked-AI":[48],"environment,":[49],"modifying":[50],"agent's":[52],"reward":[53],"strategy":[54],"account":[56],"for":[57,173],"dynamics.":[59],"Our":[60],"integration":[61],"employs":[62],"shaped":[63],"sparse":[65],"rewards":[66],"as":[67,69],"well":[68],"bonus":[71,96],"point":[72,97],"mechanism.":[73],"Rewards":[74],"are":[75],"adjusted":[76],"based":[77],"on":[78],"fluctuations":[79],"predicted":[82],"score":[84],"promote":[86],"trust-building":[87],"actions":[88],"discourage":[90],"those":[91],"that":[92,118,131],"erode":[93],"trust.":[94],"mechanism":[98],"was":[99,114,147],"intended":[100],"incentivize":[102],"maintenance":[104],"above":[107],"specified":[109],"threshold.":[110],"novel":[112],"approach":[113],"designed":[115],"ensure":[117],"RL":[120,134],"agent":[121,135,166],"prioritized":[122],"cooperation":[125],"its":[127],"decision-making.":[128],"Experiments":[129],"demonstrated":[130],"our":[132],"trustaware":[133],"outperformed":[136],"standard":[137],"non-trust-aware":[138],"agents":[139,180],"when":[140],"collaborating":[141],"with":[142],"human-proxy":[144],"agent.":[145],"evidenced":[148],"by":[149],"higher":[150],"scores":[151],"achieved":[152],"humanproxy":[154],"gaming":[155],"scenarios,":[156],"which":[157],"validated":[158],"benefits":[160],"incorporating":[162],"dynamics":[164],"learning.":[167],"work":[169],"establishes":[170],"foundation":[172],"developing":[174],"more":[175],"adaptive":[176],"trustworthy":[178],"artificial":[179],"complex":[182],"collaborative":[183],"environments.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}