{"id":"https://openalex.org/W4410297685","doi":"https://doi.org/10.1109/hri61500.2025.10974035","title":"Enabling End Users to Program Robots Using Reinforcement Learning","display_name":"Enabling End Users to Program Robots Using Reinforcement Learning","publication_year":2025,"publication_date":"2025-03-04","ids":{"openalex":"https://openalex.org/W4410297685","doi":"https://doi.org/10.1109/hri61500.2025.10974035"},"language":"en","primary_location":{"id":"doi:10.1109/hri61500.2025.10974035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri61500.2025.10974035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 20th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5025391833","display_name":"Tewodros Ayalew","orcid":"https://orcid.org/0000-0001-6929-7373"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tewodros W. Ayalew","raw_affiliation_strings":["University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109416305","display_name":"Jennifer Wang","orcid":"https://orcid.org/0009-0001-1026-2886"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jennifer Wang","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Littman","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071246801","display_name":"Blase Ur","orcid":"https://orcid.org/0000-0001-9365-3155"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Blase Ur","raw_affiliation_strings":["University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013243390","display_name":"Sarah Sebo","orcid":"https://orcid.org/0000-0003-2211-6429"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Sebo","raw_affiliation_strings":["University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06215005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"767","last_page":"777"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9922000169754028,"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":0.9922000169754028,"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9445000290870667,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9365000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7650793790817261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.710051953792572},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6407005786895752},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.520072877407074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3174405097961426}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7650793790817261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.710051953792572},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6407005786895752},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.520072877407074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3174405097961426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hri61500.2025.10974035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri61500.2025.10974035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 20th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,6],"(RL)":[2],"is":[3],"a":[4,22,85,98,117,168,177],"powerful":[5],"technique":[7],"in":[8],"robotics,":[9],"where":[10,92],"people":[11],"can":[12],"specify":[13,47],"rewards":[14],"that":[15,162,184],"robots":[16],"learn":[17],"how":[18],"to":[19,32,37,42,46,96,101,149,171,187],"maximize":[20],"through":[21],"process":[23],"of":[24,30,79,111,192],"trialanderror.":[25],"Despite":[26],"the":[27,77,138,150,189],"numerous":[28],"advantages":[29],"RL":[31,48,113,193],"robot":[33,60,100,181],"programming,":[34],"no":[35],"approaches":[36,174],"our":[38,112],"knowledge":[39],"have":[40],"sought":[41],"enable":[43],"nontechnical":[44],"users":[45,129],"programs":[49],"for":[50,63,180,194],"robots.":[51,196],"In":[52],"this":[53],"work,":[54],"we":[55,83],"designed":[56],"two":[57,81],"novel":[58],"RL-based":[59,163],"programming":[61,114,182,195],"paradigms":[62,115,164],"non-technical":[64],"users:":[65],"Full":[66],"MDP":[67,72],"Programming":[68,73,122,126],"(Full-MDP)":[69],"and":[70,143,153,175],"Goal-Only":[71],"(Goal-MDP).":[74],"To":[75],"evaluate":[76],"efficacy":[78],"these":[80],"approaches,":[82],"ran":[84],"between-subjects":[86],"online":[87],"user":[88,141],"study":[89],"($N$=":[90],"409)":[91],"participants":[93],"were":[94],"asked":[95],"program":[97],"simulated":[99],"complete":[102],"example":[103],"household":[104],"tasks":[105],"(e.g.,":[106],"delivering":[107],"coffee)":[108],"using":[109],"one":[110],"or":[116,124],"commonly":[118],"used":[119],"baseline:":[120],"Sequential":[121],"(Seq),":[123],"Trigger-Action":[125],"(TAP).":[127],"While":[128],"neither":[130],"performed":[131],"well":[132],"nor":[133],"reported":[134],"positive":[135],"experiences":[136],"with":[137,145,155],"FullMDP":[139],"interface,":[140],"performance":[142],"experience":[144],"Goal-MDP":[146,166],"was":[147],"similar":[148],"baselines":[151],"(Seq":[152],"TAP)":[154],"significantly":[156],"shorter":[157],"programs.":[158],"These":[159],"results":[160],"demonstrate":[161],"like":[165],"are":[167],"viable":[169],"alternative":[170],"more":[172],"traditional":[173],"provide":[176],"starting":[178],"point":[179],"interfaces":[183],"allow":[185],"end-users":[186],"leverage":[188],"myriad":[190],"benefits":[191]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}