{"id":"https://openalex.org/W2102847492","doi":"https://doi.org/10.1145/1390156.1390286","title":"Apprenticeship learning using linear programming","display_name":"Apprenticeship learning using linear programming","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2102847492","doi":"https://doi.org/10.1145/1390156.1390286","mag":"2102847492"},"language":"en","primary_location":{"id":"doi:10.1145/1390156.1390286","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390286","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":null,"display_name":"Umar Syed","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umar Syed","raw_affiliation_strings":["Princeton University, Princeton, NJ","Princeton Univ., Princeton , NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton Univ., Princeton , NJ","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081163135","display_name":"Michael Bowling","orcid":"https://orcid.org/0000-0003-2960-8418"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michael Bowling","raw_affiliation_strings":["University of Alberta, Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084108666","display_name":"Robert E. Schapire","orcid":"https://orcid.org/0000-0001-8616-1611"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert E. Schapire","raw_affiliation_strings":["Princeton University, Princeton, NJ","Princeton Univ., Princeton , NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton Univ., Princeton , NJ","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0452,"has_fulltext":false,"cited_by_count":196,"citation_normalized_percentile":{"value":0.97277418,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1032","last_page":"1039"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T12288","display_name":"Optimization and Search Problems","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9950000047683716,"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/apprenticeship","display_name":"Apprenticeship","score":0.807941734790802},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6794624924659729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6450891494750977},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.6004000306129456},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5892460346221924},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5432932376861572},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5084637403488159},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5037021040916443},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5021052360534668},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4487053453922272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33744147419929504},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3055489957332611},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24022537469863892},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19034484028816223},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08639690279960632}],"concepts":[{"id":"https://openalex.org/C107806365","wikidata":"https://www.wikidata.org/wiki/Q253567","display_name":"Apprenticeship","level":2,"score":0.807941734790802},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6794624924659729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6450891494750977},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.6004000306129456},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5892460346221924},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5432932376861572},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5084637403488159},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5037021040916443},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5021052360534668},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4487053453922272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33744147419929504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3055489957332611},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24022537469863892},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19034484028816223},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08639690279960632},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":3,"locations":[{"id":"doi:10.1145/1390156.1390286","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390286","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:10.1.1.149.4348","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.4348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://icml2008.cs.helsinki.fi/papers/645.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.186.1678","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.186.1678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.princeton.edu:80/%7Eschapire/papers/SyedBowlingSchapireICML2008.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1516418405","https://openalex.org/W1588345844","https://openalex.org/W1999874108","https://openalex.org/W2113023245","https://openalex.org/W2119567691","https://openalex.org/W2153816030","https://openalex.org/W2158191646","https://openalex.org/W2169498096","https://openalex.org/W2499382624","https://openalex.org/W2610857016"],"related_works":["https://openalex.org/W2130264791","https://openalex.org/W4235622043","https://openalex.org/W2155887593","https://openalex.org/W2102428166","https://openalex.org/W1600547024","https://openalex.org/W3125491562","https://openalex.org/W2315999538","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"In":[0],"apprenticeship":[1,48,98],"learning,":[2],"the":[3,33],"goal":[4],"is":[5,16,38,114],"to":[6,40,46,63,78,117,122],"learn":[7],"a":[8,11,22,51,69,123],"policy":[9,23,121],"in":[10,31,68,72,84],"Markov":[12],"decision":[13],"process":[14],"that":[15,32,57,102],"at":[17],"least":[18],"as":[19,21,50],"good":[20],"demonstrated":[24],"by":[25],"an":[26,59],"expert.":[27],"The":[28,111],"difficulty":[29],"arises":[30],"MDP's":[34],"true":[35],"reward":[36],"function":[37],"assumed":[39],"be":[41],"unknown.":[42],"We":[43],"show":[44,56],"how":[45],"frame":[47],"learning":[49,99],"linear":[52],"programming":[53],"problem,":[54],"and":[55],"using":[58],"off-the-shelf":[60],"LP":[61],"solver":[62],"solve":[64],"this":[65],"problem":[66],"results":[67],"substantial":[70],"improvement":[71],"running":[73],"time":[74],"over":[75],"existing":[76,95],"methods---up":[77],"two":[79],"orders":[80],"of":[81,108],"magnitude":[82],"faster":[83],"our":[85,88],"experiments.":[86],"Additionally,":[87],"approach":[89],"produces":[90],"stationary":[91,109,124],"policies,":[92],"while":[93],"all":[94],"methods":[96],"for":[97],"output":[100],"policies":[101],"are":[103],"\"mixed\",":[104],"i.e.":[105],"randomized":[106],"combinations":[107],"policies.":[110],"technique":[112],"used":[113],"general":[115],"enough":[116],"convert":[118],"any":[119],"mixed":[120],"policy.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":12}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}