{"id":"https://openalex.org/W4310429478","doi":"https://doi.org/10.1145/3610977.3634984","title":"Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning","display_name":"Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning","publication_year":2024,"publication_date":"2024-03-10","ids":{"openalex":"https://openalex.org/W4310429478","doi":"https://doi.org/10.1145/3610977.3634984"},"language":"en","primary_location":{"id":"doi:10.1145/3610977.3634984","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610977.3634984","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610977.3634984","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3610977.3634984","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102779488","display_name":"Tu Trinh","orcid":"https://orcid.org/0000-0002-2373-1469"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tu Trinh","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2373-1469","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067818548","display_name":"Chen Hao-yu","orcid":"https://orcid.org/0009-0007-8493-9144"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoyu Chen","raw_affiliation_strings":["University of Utah, Salt Lake City, UT, USA"],"raw_orcid":"https://orcid.org/0009-0007-8493-9144","affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103065575","display_name":"Daniel S. Brown","orcid":"https://orcid.org/0000-0002-9570-1832"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel S. Brown","raw_affiliation_strings":["University of Utah, Salt Lake City, UT, USA"],"raw_orcid":"https://orcid.org/0000-0002-9570-1832","affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"725","last_page":"733"},"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":0.9836999773979187,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9236999750137329,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8507760763168335},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.772404134273529},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6905918717384338},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6857221722602844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5845240950584412},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5715695023536682},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.556463360786438},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5202118754386902},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5109642744064331},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42752695083618164},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.42594659328460693},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.4221951961517334},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3190101385116577},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15969929099082947},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13235419988632202}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8507760763168335},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.772404134273529},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6905918717384338},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6857221722602844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5845240950584412},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5715695023536682},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.556463360786438},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5202118754386902},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5109642744064331},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42752695083618164},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42594659328460693},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.4221951961517334},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3190101385116577},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15969929099082947},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13235419988632202},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3610977.3634984","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610977.3634984","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610977.3634984","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2211.15542","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.15542","pdf_url":"https://arxiv.org/pdf/2211.15542","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3610977.3634984","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610977.3634984","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610977.3634984","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4310429478.pdf"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W147577193","https://openalex.org/W950880443","https://openalex.org/W1591675293","https://openalex.org/W1929981607","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2002206192","https://openalex.org/W2013784666","https://openalex.org/W2026400040","https://openalex.org/W2062525454","https://openalex.org/W2069855531","https://openalex.org/W2098774185","https://openalex.org/W2113023245","https://openalex.org/W2117675763","https://openalex.org/W2151516755","https://openalex.org/W2257176436","https://openalex.org/W2290104316","https://openalex.org/W2414653209","https://openalex.org/W2763110165","https://openalex.org/W2898621619","https://openalex.org/W2949963197","https://openalex.org/W2962717849","https://openalex.org/W2963208223","https://openalex.org/W2963308241","https://openalex.org/W2966120739","https://openalex.org/W2994446013","https://openalex.org/W3006303816","https://openalex.org/W3008082783","https://openalex.org/W3023565369","https://openalex.org/W3138984732","https://openalex.org/W3166618091","https://openalex.org/W3187304456","https://openalex.org/W3187722890","https://openalex.org/W3197594072","https://openalex.org/W3205824709","https://openalex.org/W4212898980","https://openalex.org/W4224057949","https://openalex.org/W4224912663","https://openalex.org/W4225737910","https://openalex.org/W4232512588","https://openalex.org/W4248056173","https://openalex.org/W4287123201","https://openalex.org/W4294959416","https://openalex.org/W4312772252","https://openalex.org/W4313529721","https://openalex.org/W4313598235","https://openalex.org/W4321153853","https://openalex.org/W4382239602","https://openalex.org/W4394666657","https://openalex.org/W6697648974"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W2807018115","https://openalex.org/W2051622126"],"abstract_inverted_index":{"We":[0,72,104,116,144],"examine":[1],"the":[2,91,131,148,168],"problem":[3],"of":[4,27,70,78,113,133],"determining":[5],"demonstration":[6,142],"sufficiency:":[7,79],"how":[8,106],"can":[9,139,150],"a":[10,24,35,67,101,135,180],"robot":[11,149,169],"self-assess":[12],"whether":[13],"it":[14],"has":[15],"received":[16],"enough":[17],"demonstrations":[18,157],"from":[19,158],"an":[20],"expert":[21],"to":[22,51,62,90,107,170,191],"ensure":[23],"desired":[25,195],"level":[26],"performance?":[28],"To":[29],"address":[30],"this":[31],"problem,":[32],"we":[33,183],"propose":[34,73],"novel":[36],"self-assessment":[37],"approach":[38,119,187],"based":[39],"on":[40,55,111],"Bayesian":[41],"inverse":[42],"reinforcement":[43],"learning":[44,153],"and":[45,58,74,96,125,129],"value-at-risk,":[46],"enabling":[47],"learning-from-demonstration":[48],"(\"LfD\")":[49],"robots":[50,190],"compute":[52],"high-confidence":[53,109],"bounds":[54,61,110],"their":[56],"performance":[57,196],"use":[59],"these":[60,114],"determine":[63],"when":[64],"they":[65],"have":[66],"sufficient":[68],"number":[69],"demonstrations.":[71,205],"evaluate":[75,117,141],"two":[76],"definitions":[77],"(1)":[80],"normalized":[81],"expected":[82],"value":[83],"difference,":[84],"which":[85,161],"measures":[86],"regret":[87],"with":[88],"respect":[89],"human's":[92],"unobserved":[93],"reward":[94],"function,":[95],"(2)":[97],"percent":[98],"improvement":[99],"over":[100],"baseline":[102],"policy.":[103,177],"demonstrate":[105],"formulate":[108],"both":[112,123],"metrics.":[115],"our":[118,186],"in":[120,154,163,175],"simulation":[121],"for":[122,156,167],"discrete":[124],"continuous":[126],"state-space":[127],"domains":[128],"illustrate":[130],"feasibility":[132],"developing":[134],"robotic":[136],"system":[137],"that":[138,147,185],"accurately":[140],"sufficiency.":[143],"also":[145],"show":[146,184],"utilize":[151],"active":[152],"asking":[155],"specific":[159],"states":[160],"results":[162],"fewer":[164],"demos":[165],"needed":[166],"still":[171],"maintain":[172],"high":[173],"confidence":[174],"its":[176],"Finally,":[178],"via":[179],"user":[181],"study,":[182],"successfully":[188],"enables":[189],"perform":[192],"at":[193],"users'":[194],"levels,":[197],"without":[198],"needing":[199],"too":[200],"many":[201],"or":[202],"perfectly":[203],"optimal":[204]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-12-10T00:00:00"}