{"id":"https://openalex.org/W4412861512","doi":"https://doi.org/10.1007/s00521-025-11477-y","title":"Single-shot policy explanation to improve task performance via semantic reward coaching","display_name":"Single-shot policy explanation to improve task performance via semantic reward coaching","publication_year":2025,"publication_date":"2025-08-02","ids":{"openalex":"https://openalex.org/W4412861512","doi":"https://doi.org/10.1007/s00521-025-11477-y"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-025-11477-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11477-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11477-y.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11477-y.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073625289","display_name":"Aaquib Tabrez","orcid":"https://orcid.org/0000-0002-4622-2894"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aaquib Tabrez","raw_affiliation_strings":["Department of Computer Science, University of Southern California, Los Angeles, United States","University of Colorado, Boulder, USA"],"raw_orcid":"https://orcid.org/0000-0002-4622-2894","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Southern California, Los Angeles, United States","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Colorado, Boulder, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082269716","display_name":"Ryan Leonard","orcid":null},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ryan Leonard","raw_affiliation_strings":["University of Colorado, Boulder, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado, Boulder, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034950112","display_name":"Bradley Hayes","orcid":"https://orcid.org/0000-0002-0723-1085"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bradley Hayes","raw_affiliation_strings":["University of Colorado, Boulder, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado, Boulder, USA","institution_ids":["https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034950112","https://openalex.org/A5073625289","https://openalex.org/A5082269716"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I188538660"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":1.2282,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84631489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"37","issue":"26","first_page":"22315","last_page":"22337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9868999719619751,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.8157497644424438},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7621569633483887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7295517325401306},{"id":"https://openalex.org/keywords/coaching","display_name":"Coaching","score":0.6869016885757446},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6380220651626587},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.449182391166687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4297439455986023},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38239818811416626},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24407273530960083},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.06786879897117615},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06539466977119446}],"concepts":[{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.8157497644424438},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7621569633483887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7295517325401306},{"id":"https://openalex.org/C2779363792","wikidata":"https://www.wikidata.org/wiki/Q1104185","display_name":"Coaching","level":2,"score":0.6869016885757446},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6380220651626587},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.449182391166687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4297439455986023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38239818811416626},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24407273530960083},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.06786879897117615},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06539466977119446},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-025-11477-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11477-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11477-y.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-025-11477-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11477-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11477-y.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2675153783","display_name":null,"funder_award_id":"W911NF-20-2-0083","funder_id":"https://openalex.org/F4320338456","funder_display_name":"DEVCOM Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320314997","display_name":"Strong","ror":"https://ror.org/041vyzr56"},{"id":"https://openalex.org/F4320338456","display_name":"DEVCOM Army Research Laboratory","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412861512.pdf","grobid_xml":"https://content.openalex.org/works/W4412861512.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1994349244","https://openalex.org/W2015153742","https://openalex.org/W2018094844","https://openalex.org/W2044140042","https://openalex.org/W2076337359","https://openalex.org/W2087484885","https://openalex.org/W2111040806","https://openalex.org/W2144001787","https://openalex.org/W2157289187","https://openalex.org/W2264742718","https://openalex.org/W2282821441","https://openalex.org/W2337392266","https://openalex.org/W2396746452","https://openalex.org/W2470650155","https://openalex.org/W2583271265","https://openalex.org/W2594336441","https://openalex.org/W2735318784","https://openalex.org/W2887260263","https://openalex.org/W2888420917","https://openalex.org/W2898694742","https://openalex.org/W2915495256","https://openalex.org/W2928096804","https://openalex.org/W2931618942","https://openalex.org/W2935359041","https://openalex.org/W2962858109","https://openalex.org/W2963095307","https://openalex.org/W2963395533","https://openalex.org/W2963672746","https://openalex.org/W2974071289","https://openalex.org/W2989822567","https://openalex.org/W3026334498","https://openalex.org/W3040802234","https://openalex.org/W3082884068","https://openalex.org/W3093033010","https://openalex.org/W3113260814","https://openalex.org/W3183109154","https://openalex.org/W4225093764","https://openalex.org/W4243705605","https://openalex.org/W4254148040","https://openalex.org/W4285151373","https://openalex.org/W4288083537","https://openalex.org/W4312433264","https://openalex.org/W4372300294","https://openalex.org/W4383108651","https://openalex.org/W4385403831","https://openalex.org/W4389121755","https://openalex.org/W4390636037","https://openalex.org/W4392634017","https://openalex.org/W4399353402","https://openalex.org/W6608836677","https://openalex.org/W6609232642","https://openalex.org/W6753134527"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W4249854088","https://openalex.org/W2746413784","https://openalex.org/W2773965352","https://openalex.org/W603502240","https://openalex.org/W2051499216","https://openalex.org/W656132696","https://openalex.org/W4232010708","https://openalex.org/W2748672977"],"abstract_inverted_index":{"Abstract":[0],"Communication":[1],"is":[2,26],"crucial":[3],"for":[4,58],"synchronizing":[5],"expectations":[6],"and":[7,45,99,123,139,148,184,194],"knowledge":[8],"within":[9],"teams.":[10],"For":[11],"robots":[12],"to":[13,23,32,36,77,86,156,161,165,180],"effectively":[14],"collaborate":[15],"with":[16,134],"or":[17,21],"provide":[18],"actionable":[19,163],"decision-support":[20],"coaching":[22],"humans,":[24],"it":[25],"critical":[27],"that":[28,46,67],"they":[29],"be":[30],"able":[31],"generate":[33],"intelligible":[34],"explanations":[35,70],"reconcile":[37],"differences":[38],"between":[39],"their":[40,48,84,103],"understanding":[41],"of":[42,47,74,111,116,127,132,172],"the":[43,112],"world":[44],"collaborators.":[49],"In":[50],"this":[51],"work":[52],"we":[53,176,202],"present":[54,107],"Single-shot":[55],"Policy":[56],"Elicitation":[57],"Augmenting":[59],"Rewards":[60],"(SPEAR),":[61],"a":[62,119,124,130,170,206],"novel":[63],"sequential":[64],"optimization":[65],"algorithm":[66],"uses":[68],"semantic":[69],"derived":[71],"from":[72],"combinations":[73],"planning":[75],"predicates":[76],"augment":[78],"human":[79,167,173,182],"agents\u2019":[80],"reward":[81,104],"functions,":[82],"driving":[83],"policies":[85,183],"exhibit":[87],"more":[88],"optimal":[89],"behavior":[90],"by":[91],"modeling":[92],"humans":[93],"as":[94],"reinforcement":[95],"learning":[96],"(RL)":[97],"agents":[98],"reconciling":[100],"disparities":[101],"in":[102,118,146,205,214],"function.":[105],"We":[106],"an":[108,153],"experimental":[109],"validation":[110],"policy":[113,208],"manipulation":[114,209],"capabilities":[115],"SPEAR":[117,128,142,204],"practically":[120],"grounded":[121],"application":[122],"performance":[125],"analysis":[126],"across":[129],"suite":[131],"domains":[133],"increasingly":[135],"complex":[136],"state":[137],"spaces":[138],"predicate":[140],"counts.":[141],"demonstrates":[143],"substantial":[144],"improvements":[145],"runtime":[147],"addressable":[149],"problem":[150],"size,":[151],"enabling":[152],"expert":[154],"agent":[155],"leverage":[157],"its":[158,212],"own":[159],"expertise":[160],"communicate":[162],"information":[164],"improve":[166,181],"performance.":[168],"Through":[169],"series":[171],"subjects":[174],"studies,":[175],"demonstrate":[177],"SPEAR\u2019s":[178],"potential":[179],"reduce":[185],"cognitive":[186],"load,":[187],"all":[188],"while":[189],"enhancing":[190],"interpretability,":[191],"task":[192],"awareness,":[193],"promoting":[195],"active":[196],"thinking":[197],"patterns":[198],"among":[199],"users.":[200],"Finally,":[201],"apply":[203],"robot-to-robot":[207],"scenario,":[210],"showcasing":[211],"applicability":[213],"robot-robot":[215],"collaborations.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}