{"id":"https://openalex.org/W4412536316","doi":"https://doi.org/10.1109/lcsys.2025.3591199","title":"Robust Human-Machine Teaming Through Reinforcement Learning From Failure via Sparse Reward Densification","display_name":"Robust Human-Machine Teaming Through Reinforcement Learning From Failure via Sparse Reward Densification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412536316","doi":"https://doi.org/10.1109/lcsys.2025.3591199"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2025.3591199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2025.3591199","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","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/A5101438487","display_name":"MingKang Wu","orcid":"https://orcid.org/0009-0004-2960-0787"},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mingkang Wu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at San Antonio, San Antonio, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at San Antonio, San Antonio, TX, USA","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014808989","display_name":"Yongcan Cao","orcid":"https://orcid.org/0000-0003-3383-0185"},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongcan Cao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at San Antonio, San Antonio, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at San Antonio, San Antonio, TX, USA","institution_ids":["https://openalex.org/I45438204"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101438487"],"corresponding_institution_ids":["https://openalex.org/I45438204"],"apc_list":null,"apc_paid":null,"fwci":1.1617,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80341166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"9","issue":null,"first_page":"2315","last_page":"2320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9510999917984009,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9510999917984009,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9348000288009644,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9028000235557556,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6401774883270264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.547627329826355},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5326336026191711},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4934472143650055},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4361557364463806},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.27408984303474426},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09033188223838806}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6401774883270264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.547627329826355},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5326336026191711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4934472143650055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4361557364463806},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27408984303474426},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09033188223838806}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2025.3591199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2025.3591199","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G454115922","display_name":null,"funder_award_id":"W911NF2310363","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7298247483","display_name":null,"funder_award_id":"N000142212474","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8692803931","display_name":null,"funder_award_id":"W911NF2110103","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1622676895","https://openalex.org/W2150468603","https://openalex.org/W2788862220","https://openalex.org/W2962787969","https://openalex.org/W2963099939","https://openalex.org/W3003474222","https://openalex.org/W3096831136","https://openalex.org/W4317584472","https://openalex.org/W4393147692","https://openalex.org/W4400526468"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Learning":[0],"control":[1,14,36,197],"policies":[2,37],"in":[3,29,88],"sparse":[4,168],"reward":[5,55,131,154,193],"environments":[6,166],"is":[7,50,76,187],"a":[8,129,136],"challenging":[9],"task":[10],"for":[11,165],"many":[12],"robotic":[13],"tasks.":[15],"The":[16],"existing":[17],"studies":[18],"focus":[19],"on":[20,190],"designing":[21],"reinforcement":[22],"learning":[23],"algorithms":[24],"that":[25,35,57,134],"take":[26],"human":[27,74],"inputs":[28],"the":[30,42,71,84,105,140,143,177,180,191,196,208,211],"form":[31],"of":[32,44,73,86,107,179,210],"demonstrations":[33,61,75],"such":[34],"are":[38,62],"learned":[39],"via":[40,170],"uncovering":[41],"value":[43,178],"these":[45,89],"demonstrations.":[46,123],"One":[47],"typical":[48],"approach":[49,213],"to":[51,81,97,104,120,138,161,194,206],"learn":[52],"an":[53,158],"inherent":[54],"function":[56],"can":[58],"explain":[59],"why":[60],"better":[63],"than":[64,116],"other":[65],"randomly":[66],"generated":[67],"samples.":[68],"Albeit":[69],"powerful,":[70],"use":[72,98],"typically":[77],"costly":[78],"and":[79,147],"difficult":[80],"collect,":[82],"indicating":[83],"lack":[85],"robustness":[87],"studies.":[90],"To":[91],"enhance":[92],"robustness,":[93],"we":[94],"here":[95],"propose":[96],"failed":[99],"experiences,":[100],"namely,":[101],"failure,":[102],"due":[103],"easiness":[106],"obtaining":[108],"failure":[109,148],"dataset,":[110],"requiring":[111],"only":[112],"common":[113],"sense":[114],"rather":[115],"domain":[117],"knowledge":[118],"needed":[119],"generate":[121],"expert":[122],"In":[124],"particular,":[125],"this":[126],"paper":[127],"proposes":[128],"new":[130],"densification":[132,155],"technique":[133,156],"trains":[135],"discriminator":[137],"evaluate":[139],"similarity":[141],"between":[142],"agent\u2019s":[144],"current":[145,181],"behavior":[146],"dataset":[149],"provided":[150],"by":[151,214],"humans.":[152],"This":[153],"provides":[157],"effective":[159],"mechanism":[160],"obtain":[162],"state-action":[163],"values":[164],"with":[167,174,216],"rewards,":[169],"quantifying":[171],"their":[172],"(dis)similarity":[173],"failure.":[175],"Additionally,":[176],"behavior,":[182],"formulated":[183],"as":[184],"advantage":[185],"function,":[186],"employed":[188],"based":[189],"densified":[192],"refine":[195],"policy\u2019s":[198],"search":[199],"direction.":[200],"We":[201],"finally":[202],"conduct":[203],"several":[204],"experiments":[205],"demonstrate":[207],"effectiveness":[209],"proposed":[212],"comparing":[215],"state-of-art":[217],"methods.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}