{"id":"https://openalex.org/W2135043890","doi":"https://doi.org/10.1145/1390156.1390175","title":"Learning for control from multiple demonstrations","display_name":"Learning for control from multiple demonstrations","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2135043890","doi":"https://doi.org/10.1145/1390156.1390175","mag":"2135043890"},"language":"en","primary_location":{"id":"doi:10.1145/1390156.1390175","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","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/A5103153292","display_name":"Adam Coates","orcid":"https://orcid.org/0000-0002-4004-1603"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Coates","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112456378","display_name":"Andrew Y. Ng","orcid":"https://orcid.org/0000-0001-5547-3196"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Y. Ng","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":14.8562,"has_fulltext":false,"cited_by_count":235,"citation_normalized_percentile":{"value":0.99496289,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9983999729156494,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9983999729156494,"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":0.9932000041007996,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9894999861717224,"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/trajectory","display_name":"Trajectory","score":0.8698708415031433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5994574427604675},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5237512588500977},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5211922526359558},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.47955819964408875},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.46471723914146423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45244118571281433},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4478597640991211},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4138530492782593},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.25927650928497314},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.21140044927597046},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1529286801815033},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13250651955604553}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.8698708415031433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5994574427604675},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5237512588500977},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5211922526359558},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.47955819964408875},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.46471723914146423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45244118571281433},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4478597640991211},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4138530492782593},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25927650928497314},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.21140044927597046},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1529286801815033},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13250651955604553},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1390156.1390175","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.3114","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.3114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://heli.stanford.edu/papers/coatesabbeelng_icml2008.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W143558673","https://openalex.org/W658381347","https://openalex.org/W1540685400","https://openalex.org/W1544444076","https://openalex.org/W1544729927","https://openalex.org/W1591675293","https://openalex.org/W1596805757","https://openalex.org/W1597173708","https://openalex.org/W1689445748","https://openalex.org/W1949804828","https://openalex.org/W1999874108","https://openalex.org/W2012302913","https://openalex.org/W2049633694","https://openalex.org/W2061562262","https://openalex.org/W2074231493","https://openalex.org/W2113023245","https://openalex.org/W2116442740","https://openalex.org/W2128160875","https://openalex.org/W2128677288","https://openalex.org/W2132602063","https://openalex.org/W2155357014","https://openalex.org/W2169080882","https://openalex.org/W2169209873","https://openalex.org/W2169498096"],"related_works":["https://openalex.org/W4385832323","https://openalex.org/W4244391535","https://openalex.org/W2356996864","https://openalex.org/W2904060783","https://openalex.org/W2015393961","https://openalex.org/W2378339670","https://openalex.org/W2359353485","https://openalex.org/W2361427670","https://openalex.org/W2139910871","https://openalex.org/W2119925415"],"abstract_inverted_index":{"We":[0,22,50],"consider":[1],"the":[2,33,47,55,64,82,93],"problem":[3,56],"of":[4,16,57,70],"learning":[5],"to":[6,54],"follow":[7],"a":[8,13,19,40,115],"desired":[9],"trajectory":[10,31],"when":[11],"given":[12],"small":[14],"number":[15],"demonstrations":[17,36],"from":[18,32],"sub-optimal":[20,34],"expert.":[21],"present":[23],"an":[24],"algorithm":[25,53],"that":[26,69],"(i)":[27],"extracts":[28],"the---initially":[29],"unknown---desired":[30],"expert's":[35],"and":[37,98,112,114,124],"(ii)":[38],"learns":[39],"local":[41],"model":[42],"suitable":[43],"for":[44],"control":[45],"along":[46],"learned":[48],"trajectory.":[49],"apply":[51],"our":[52,71,78,90],"autonomous":[58,65,85,95,120],"helicopter":[59,73,86],"flight.":[60],"In":[61,88],"all":[62],"cases,":[63],"helicopter's":[66],"performance":[67,102],"exceeds":[68],"expert":[72],"pilot's":[74],"demonstrations.":[75],"Even":[76],"stronger,":[77],"results":[79,91],"significantly":[80],"extend":[81],"state-of-the-art":[83],"in":[84],"aerobatics.":[87],"particular,":[89],"include":[92],"first":[94],"tic-tocs,":[96],"loops":[97],"hurricane,":[99],"vastly":[100],"superior":[101],"on":[103],"previously":[104],"performed":[105],"aerobatic":[106],"maneuvers":[107],"(such":[108],"as":[109],"in-place":[110],"flips":[111],"rolls),":[113],"complete":[116],"airshow,":[117],"which":[118],"requires":[119],"transitions":[121],"between":[122],"these":[123],"various":[125],"other":[126],"maneuvers.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":24},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":14}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}