{"id":"https://openalex.org/W1971890413","doi":"https://doi.org/10.1145/1329125.1329407","title":"Confidence-based policy learning from demonstration using Gaussian mixture models","display_name":"Confidence-based policy learning from demonstration using Gaussian mixture models","publication_year":2007,"publication_date":"2007-05-14","ids":{"openalex":"https://openalex.org/W1971890413","doi":"https://doi.org/10.1145/1329125.1329407","mag":"1971890413"},"language":"en","primary_location":{"id":"doi:10.1145/1329125.1329407","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1329125.1329407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems","raw_type":"proceedings-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/A5033265891","display_name":"Sonia Chernova","orcid":"https://orcid.org/0000-0001-6320-0825"},"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":true,"raw_author_name":"Sonia Chernova","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088276691","display_name":"Manuela Veloso","orcid":"https://orcid.org/0000-0001-6738-238X"},"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":"Manuela Veloso","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033265891"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":15.4763,"has_fulltext":false,"cited_by_count":164,"citation_normalized_percentile":{"value":0.98964978,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9925000071525574,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9925000071525574,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9861999750137329,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9840999841690063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8157553672790527},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7406446933746338},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.655478835105896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6344457864761353},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5908651947975159},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5809615850448608},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.531448483467102},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.47044438123703003},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44584524631500244},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.44188961386680603},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.44030076265335083},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4272172451019287},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.42419183254241943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8157553672790527},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7406446933746338},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.655478835105896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6344457864761353},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5908651947975159},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5809615850448608},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.531448483467102},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.47044438123703003},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44584524631500244},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.44188961386680603},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.44030076265335083},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4272172451019287},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.42419183254241943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1329125.1329407","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1329125.1329407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.68.5154","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.68.5154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/afs/cs/user/mmv/www/papers/07aamas-sonia.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G3965011487","display_name":null,"funder_award_id":"NBCH-1040007","funder_id":"https://openalex.org/F4320306116","funder_display_name":"U.S. Department of the Interior"}],"funders":[{"id":"https://openalex.org/F4320306116","display_name":"U.S. Department of the Interior","ror":"https://ror.org/03v0pmy70"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W199774983","https://openalex.org/W1520096009","https://openalex.org/W1540685400","https://openalex.org/W1965218672","https://openalex.org/W1977546238","https://openalex.org/W1999874108","https://openalex.org/W2048226872","https://openalex.org/W2049633694","https://openalex.org/W2102384057","https://openalex.org/W2103285838","https://openalex.org/W2104308387","https://openalex.org/W2108157636","https://openalex.org/W2116165953","https://openalex.org/W2129186586","https://openalex.org/W2130726249","https://openalex.org/W2142635246","https://openalex.org/W2148161811","https://openalex.org/W2154342426","https://openalex.org/W2159080219","https://openalex.org/W2166698530","https://openalex.org/W2303345904","https://openalex.org/W2797746357","https://openalex.org/W4250143236","https://openalex.org/W4376496912","https://openalex.org/W4388365263","https://openalex.org/W6608174230","https://openalex.org/W6632235069","https://openalex.org/W6676314958","https://openalex.org/W6682050375","https://openalex.org/W6738852829","https://openalex.org/W7024454421","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W1992295166","https://openalex.org/W2143508933","https://openalex.org/W2953364237"],"abstract_inverted_index":{"We":[0,70,168],"contribute":[1],"an":[2,13],"approach":[3,171],"for":[4,66,94,98,148],"interactive":[5],"policy":[6,36],"learning":[7,79],"through":[8],"expert":[9],"demonstration":[10,21,59,109,163],"that":[11],"allows":[12],"agent":[14,89,106,140],"to":[15,25,53,90],"actively":[16],"request":[17,96],"and":[18,95,110,133,155,161,176],"effectively":[19],"represent":[20,34],"examples.":[22],"In":[23],"order":[24],"address":[26],"the":[27,35,67,84,88,92,102,118,121,139,146,158,162,166],"inherent":[28],"uncertainty":[29,119],"of":[30,40,83,101,117,120,151,165],"human":[31],"demonstration,":[32],"we":[33],"as":[37,63],"a":[38,54],"set":[39],"Gaussian":[41,50,123],"mixture":[42,124],"models":[43],"(GMMs),":[44],"where":[45],"each":[46],"model,":[47],"with":[48,142,172],"multiple":[49],"components,":[51],"corresponds":[52],"single":[55],"action.":[56],"Incrementally":[57],"received":[58],"examples":[60],"are":[61],"used":[62],"training":[64,159],"data":[65],"GMM":[68],"set.":[69,125],"then":[71],"introduce":[72],"our":[73,170],"confident":[74],"execution":[75,112],"approach,":[76],"which":[77],"focuses":[78],"on":[80,114],"relevant":[81],"parts":[82,100],"domain":[85],"by":[86],"enabling":[87],"identify":[91],"need":[93,147],"demonstrations":[97,150],"specific":[99],"state":[103],"space.":[104],"The":[105],"selects":[107],"between":[108],"autonomous":[111],"based":[113],"statistical":[115],"analysis":[116],"learned":[122],"As":[126],"it":[127],"achieves":[128],"proficiency":[129],"at":[130],"its":[131,137],"task":[132],"gains":[134],"confidence":[135],"in":[136,174],"actions,":[138],"operates":[141],"increasing":[143],"autonomy,":[144],"eliminating":[145],"unnecessary":[149],"already":[152],"acquired":[153],"behavior,":[154],"reducing":[156],"both":[157],"time":[160],"workload":[164],"expert.":[167],"validate":[169],"experiments":[173],"simulated":[175],"real":[177],"robot":[178],"domains.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}