{"id":"https://openalex.org/W4411176198","doi":"https://doi.org/10.1145/3743150","title":"Improving the Transparency of Robot Policies Using Demonstrations and Reward Communication","display_name":"Improving the Transparency of Robot Policies Using Demonstrations and Reward Communication","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4411176198","doi":"https://doi.org/10.1145/3743150"},"language":"en","primary_location":{"id":"doi:10.1145/3743150","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743150","pdf_url":null,"source":{"id":"https://openalex.org/S4210193251","display_name":"ACM Transactions on Human-Robot Interaction","issn_l":"2573-9522","issn":["2573-9522"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Human-Robot Interaction","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/A5091719119","display_name":"M.H. Lee","orcid":"https://orcid.org/0009-0008-8659-3041"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael S. Lee","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"raw_orcid":"https://orcid.org/0009-0008-8659-3041","affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064960456","display_name":"Reid Simmons","orcid":"https://orcid.org/0000-0003-3153-0453"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reid Simmons","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"raw_orcid":"https://orcid.org/0000-0003-3153-0453","affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061653312","display_name":"Henny Admoni","orcid":"https://orcid.org/0000-0003-1796-2196"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henny Admoni","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"raw_orcid":"https://orcid.org/0000-0003-1796-2196","affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84086094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"14","issue":"4","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.98580002784729,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9724000096321106,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.9022101163864136},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6027059555053711},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5169503092765808},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4610348045825958},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.40995603799819946},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.329456627368927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2707363963127136},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1903589367866516}],"concepts":[{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.9022101163864136},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6027059555053711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5169503092765808},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4610348045825958},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.40995603799819946},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.329456627368927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2707363963127136},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1903589367866516}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743150","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743150","pdf_url":null,"source":{"id":"https://openalex.org/S4210193251","display_name":"ACM Transactions on Human-Robot Interaction","issn_l":"2573-9522","issn":["2573-9522"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Human-Robot Interaction","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W190293641","https://openalex.org/W605243474","https://openalex.org/W1490308602","https://openalex.org/W1517053320","https://openalex.org/W1968669537","https://openalex.org/W1999874108","https://openalex.org/W2020229731","https://openalex.org/W2039000252","https://openalex.org/W2040196349","https://openalex.org/W2073583237","https://openalex.org/W2098875425","https://openalex.org/W2106779500","https://openalex.org/W2133705455","https://openalex.org/W2134888964","https://openalex.org/W2135943618","https://openalex.org/W2137966130","https://openalex.org/W2154424448","https://openalex.org/W2166815260","https://openalex.org/W2167362547","https://openalex.org/W2275060590","https://openalex.org/W2499811908","https://openalex.org/W2574287525","https://openalex.org/W2594227402","https://openalex.org/W2622408375","https://openalex.org/W2766447205","https://openalex.org/W2779206865","https://openalex.org/W2782898451","https://openalex.org/W2783539613","https://openalex.org/W2889262248","https://openalex.org/W2897798332","https://openalex.org/W2949693231","https://openalex.org/W2963149119","https://openalex.org/W2963395533","https://openalex.org/W2963411833","https://openalex.org/W2965912206","https://openalex.org/W2966578325","https://openalex.org/W2972018816","https://openalex.org/W2991044292","https://openalex.org/W3082925502","https://openalex.org/W3101780148","https://openalex.org/W3124922852","https://openalex.org/W3163411042","https://openalex.org/W3164011142","https://openalex.org/W3174286486","https://openalex.org/W3213657171","https://openalex.org/W4214717370","https://openalex.org/W4235114045","https://openalex.org/W4235762696","https://openalex.org/W4285151373","https://openalex.org/W4310108479","https://openalex.org/W4386193536","https://openalex.org/W4400518895"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3081288631","https://openalex.org/W3152382318","https://openalex.org/W3004686567","https://openalex.org/W2738656338","https://openalex.org/W2603787370","https://openalex.org/W2555400967","https://openalex.org/W3214759741","https://openalex.org/W3174876210"],"abstract_inverted_index":{"Demonstrations":[0],"are":[1,95],"a":[2,17,39,45,77,149],"powerful":[3],"way":[4],"to":[5,9,71,91],"teach":[6],"robot":[7],"decision-making":[8],"humans.":[10],"Although":[11],"informative":[12],"demonstrations":[13,43,93],"may":[14,26],"be":[15],"selected":[16],"priori":[18],"using":[19],"the":[20,29,53,58,64,73,86,98,116,119,144,171,184,188,204],"machine":[21],"teaching":[22,47,113,136,158,175,185,202],"framework,":[23],"student":[24],"learning":[25,87,197],"deviate":[27],"from":[28,52,170,199],"pre-selected":[30,42],"curriculum":[31,40],"in":[32,102,148,191,203],"situ.":[33],"This":[34],"article":[35],"thus":[36],"explores":[37],"augmenting":[38],"of":[41,60,82,121,141,173],"with":[44],"closed-loop":[46,112,135,157],"framework":[48,114,137],"inspired":[49],"by":[50,125,163],"principles":[51],"education":[54],"literature,":[55],"such":[56],"as":[57],"zone":[59],"proximal":[61],"development":[62],"and":[63,75,187],"testing":[65],"effect.":[66],"We":[67,131,153],"utilize":[68],"tests":[69],"accordingly":[70],"close":[72],"loop":[74],"maintain":[76],"novel":[78],"particle":[79],"filter":[80],"model":[81],"human":[83,122],"beliefs":[84],"throughout":[85],"process,":[88],"allowing":[89],"us":[90],"provide":[92],"that":[94,109,155],"targeted":[96],"at":[97],"human\u2019s":[99],"current":[100],"understanding":[101],"real":[103],"time.":[104],"A":[105],"user":[106,151,193],"study":[107],"finds":[108],"our":[110,134,156],"proposed":[111],"reduces":[115],"regret":[117],"(i.e.,":[118],"suboptimality)":[120],"test":[123],"responses":[124],"43%":[126],"over":[127],"an":[128],"open-loop":[129],"baseline.":[130],"also":[132,167],"compare":[133],"against":[138],"another":[139],"baseline":[140],"directly":[142],"communicating":[143],"robot\u2019s":[145],"reward":[146,161],"function":[147],"second":[150],"study.":[152],"find":[154],"outperforms":[159],"direct":[160],"communication":[162],"64%,":[164],"but":[165],"we":[166,178],"observe":[168,179],"synergies":[169],"use":[172],"both":[174,192],"forms.":[176],"Finally,":[177],"strong":[180],"interaction":[181],"effects":[182],"between":[183],"form":[186],"domains":[189],"considered":[190],"studies,":[194],"seeing":[195],"increased":[196],"outcomes":[198],"well-designed":[200],"demonstration-based":[201],"more":[205],"challenging":[206],"domain.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}