{"id":"https://openalex.org/W2571465252","doi":"https://doi.org/10.1109/cdc.2016.7799361","title":"Learning parameterized policies for Markov decision processes through demonstrations","display_name":"Learning parameterized policies for Markov decision processes through demonstrations","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2571465252","doi":"https://doi.org/10.1109/cdc.2016.7799361","mag":"2571465252"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2016.7799361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7799361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","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/A5057858044","display_name":"Manjesh K. Hanawal","orcid":"https://orcid.org/0000-0002-1807-5487"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manjesh K. Hanawal","raw_affiliation_strings":["IEOR, IIT-Bombay, Powai, MH, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IEOR, IIT-Bombay, Powai, MH, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458867","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0003-0510-6501"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China","Department of Electrical and Computer Engineering, Boston University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054049845","display_name":"Henghui Zhu","orcid":"https://orcid.org/0000-0002-4534-6975"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henghui Zhu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Boston University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075696701","display_name":"Ioannis Ch. Paschalidis","orcid":"https://orcid.org/0000-0002-3343-2913"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioannis Ch. Paschalidis","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Boston University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":null,"first_page":"7087","last_page":"7092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9972000122070312,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9814000129699707,"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/markov-chain","display_name":"Markov chain","score":0.7410566806793213},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.7002344131469727},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6129661798477173},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5951201319694519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.547444224357605},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5191494822502136},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.49032166600227356},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4406777620315552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4115650951862335},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.39594295620918274},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3791406452655792},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34381407499313354},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20168524980545044},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1916547417640686}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.7410566806793213},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7002344131469727},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6129661798477173},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5951201319694519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.547444224357605},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5191494822502136},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.49032166600227356},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4406777620315552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4115650951862335},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39594295620918274},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3791406452655792},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34381407499313354},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20168524980545044},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1916547417640686},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2016.7799361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7799361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1931877416","https://openalex.org/W1983161979","https://openalex.org/W1986014385","https://openalex.org/W2004915807","https://openalex.org/W2061562262","https://openalex.org/W2099111195","https://openalex.org/W2116442740","https://openalex.org/W2166302491","https://openalex.org/W2326968954","https://openalex.org/W2334782222","https://openalex.org/W2478708596","https://openalex.org/W2950989964","https://openalex.org/W2962957031","https://openalex.org/W4205326910","https://openalex.org/W4251784400","https://openalex.org/W6640174482","https://openalex.org/W6677631742","https://openalex.org/W6701398536"],"related_works":["https://openalex.org/W4287863949","https://openalex.org/W4287102143","https://openalex.org/W1850488217","https://openalex.org/W2945119207","https://openalex.org/W3182614517","https://openalex.org/W2049472152","https://openalex.org/W1974307281","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"We":[0,20,49,115],"consider":[1],"the":[2,44,51,57,60,67,74,89,98,108,112,117],"problem":[3],"of":[4,25,56,66,73,97,101,111,119],"learning":[5],"a":[6,13,23,39,123],"policy":[7,40,62],"used":[8],"by":[9],"an":[10],"agent":[11],"in":[12,53,64],"Markov":[14,75,102,113],"decision":[15],"process":[16],"using":[17],"state-action":[18,46],"samples.":[19],"focus":[21],"on":[22,122],"class":[24],"parameterized":[26],"policies":[27],"and":[28,59,70,92],"use":[29,79],"\u2113":[30],"<sub":[31],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[32],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sub>":[33],"-regularized":[34],"logistic":[35],"regression":[36],"to":[37,85,88,104,107],"train":[38],"that":[41],"best":[42],"fits":[43],"observed":[45],"pairs":[47],"(demonstrations).":[48],"bound":[50],"difference":[52],"average":[54],"reward":[55],"trained":[58],"original":[61],"(regret)":[63],"terms":[65],"generalization":[68,90],"error":[69,91],"sensitivity":[71,95],"parameters":[72],"chain.":[76,114],"Specifically,":[77],"we":[78],"techniques":[80,93],"from":[81,94],"sample":[82],"complexity":[83],"theory":[84],"relate":[86,105],"regret":[87,106],"analysis":[96],"stationary":[99],"distribution":[100],"chains":[103],"ergodic":[109],"coefficient":[110],"demonstrate":[116],"effectiveness":[118],"our":[120],"method":[121],"synthetic":[124],"example.":[125]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}