{"id":"https://openalex.org/W2964025922","doi":"https://doi.org/10.48550/arxiv.1805.10413","title":"Fast Policy Learning through Imitation and Reinforcement","display_name":"Fast Policy Learning through Imitation and Reinforcement","publication_year":2018,"publication_date":"2018-05-26","ids":{"openalex":"https://openalex.org/W2964025922","doi":"https://doi.org/10.48550/arxiv.1805.10413","mag":"2964025922"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1805.10413","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.10413","pdf_url":"https://arxiv.org/pdf/1805.10413","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1805.10413","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101825910","display_name":"Ching-An Cheng","orcid":"https://orcid.org/0000-0002-0610-2070","observed_orcids":["https://orcid.org/0000-0002-0610-2070"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng, Ching-An","raw_affiliation_strings":["Georgia Tech Atlanta , GA 30332","Georgia Institute of Technology, Atlanta, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech Atlanta , GA 30332","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078753151","display_name":"Xinyan Yan","orcid":"https://orcid.org/0000-0003-4082-084X","observed_orcids":["https://orcid.org/0000-0003-4082-084X"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan, Xinyan","raw_affiliation_strings":["Georgia Tech Atlanta , GA 30332","Georgia Institute of Technology, Atlanta, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech Atlanta , GA 30332","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010914575","display_name":"Nolan Wagener","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wagener, Nolan","raw_affiliation_strings":["Byron Boots Georgia Tech Atlanta , GA 30332","Georgia Tech Atlanta , GA 30332","Georgia Institute of Technology, Atlanta, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Byron Boots Georgia Tech Atlanta , GA 30332","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Tech Atlanta , GA 30332","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110797782","display_name":"Byron Boots","orcid":"https://orcid.org/0000-0003-3950-572X","observed_orcids":["https://orcid.org/0000-0003-3950-572X"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boots, Byron","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, United States","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":62,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"845","last_page":"855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/imitation-learning","display_name":"imitation learning","score":0.9940000176429749},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9909999966621399},{"id":"https://openalex.org/keywords/hybrid-learning","display_name":"hybrid learning","score":0.5040000081062317},{"id":"https://openalex.org/keywords/mirror-descent","display_name":"mirror descent","score":0.8619999885559082},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.6549999713897705},{"id":"https://openalex.org/keywords/loki","display_name":"Loki","score":0.7440000176429749},{"id":"https://openalex.org/keywords/policy-learning","display_name":"policy learning","score":0.4230000078678131},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.6899999976158142}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8342075347900391},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7962936162948608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734044075012207},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5906698703765869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.587722659111023},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5571776032447815},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.504313588142395},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.4985177516937256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44328221678733826},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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},{"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1805.10413","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.10413","pdf_url":"https://arxiv.org/pdf/1805.10413","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.1805.10413","doi":"https://doi.org/10.48550/arxiv.1805.10413","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.10413","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2964025922","doi":null,"is_oa":false,"landing_page_url":"http://auai.org/uai2018/proceedings/papers/302.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306421103","display_name":"Uncertainty in Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Uncertainty in Artificial Intelligence","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1805.10413","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.10413","pdf_url":"https://arxiv.org/pdf/1805.10413","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6320469489","display_name":"CAREER:Designing Robots that Learn: Closing the Gap Between Machine Learning and Engineering","funder_award_id":"1750483","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6649578213","display_name":"NRI: Collaborative Research: Accelerating Robotic Manipulation with Data-Enhanced Contact Mechanics","funder_award_id":"1637758","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W112666333","https://openalex.org/W1191599655","https://openalex.org/W1499669280","https://openalex.org/W1529094214","https://openalex.org/W1575592356","https://openalex.org/W1757796397","https://openalex.org/W1850531616","https://openalex.org/W1931877416","https://openalex.org/W1992208280","https://openalex.org/W2032916024","https://openalex.org/W2033468335","https://openalex.org/W2108682071","https://openalex.org/W2130801532","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2165150801","https://openalex.org/W2166302491","https://openalex.org/W2260756217","https://openalex.org/W2594640072","https://openalex.org/W2602076750","https://openalex.org/W2756826236","https://openalex.org/W2757631751","https://openalex.org/W2767002724","https://openalex.org/W2772709170","https://openalex.org/W2784825028","https://openalex.org/W2793955514","https://openalex.org/W2949608212","https://openalex.org/W3037207827","https://openalex.org/W3096194929","https://openalex.org/W6960125083"],"related_works":["https://openalex.org/W7097368714","https://openalex.org/W3039781880","https://openalex.org/W2347074400","https://openalex.org/W4416159171","https://openalex.org/W4405955696","https://openalex.org/W2942910319","https://openalex.org/W2946160813","https://openalex.org/W7133183494","https://openalex.org/W4387355866","https://openalex.org/W3130842663"],"abstract_inverted_index":{"Imitation":[0],"learning":[1,33,92],"(IL)":[2],"consists":[3],"of":[4,7,49,101,144],"a":[5,65,78,81,88,96,107,127],"set":[6],"tools":[8],"that":[9,44,71,93,114],"leverage":[10],"expert":[11,20,129],"demonstrations":[12],"to":[13,31,40,106,125],"quickly":[14],"learn":[15,124],"policies.":[16],"However,":[17],"if":[18,115],"the":[19,46,116,142],"is":[21,119],"suboptimal,":[22],"IL":[23,62,102],"can":[24,74,123],"yield":[25],"policies":[26],"with":[27],"inferior":[28],"performance":[29,143],"compared":[30],"reinforcement":[32],"(RL).":[34],"In":[35],"this":[36,55],"paper,":[37],"we":[38,140],"aim":[39],"provide":[41],"an":[42],"algorithm":[43],"combines":[45],"best":[47],"aspects":[48],"RL":[50,60,110],"and":[51,61,130],"IL.":[52],"We":[53,84,112],"accomplish":[54],"by":[56],"formulating":[57],"several":[58,148],"popular":[59],"algorithms":[63,73],"in":[64,147],"common":[66],"mirror":[67],"descent":[68],"framework,":[69],"showing":[70],"these":[72],"be":[75],"viewed":[76],"as":[77],"variation":[79],"on":[80],"single":[82],"approach.":[83],"then":[85],"propose":[86],"LOKI,":[87],"strategy":[89],"for":[90],"policy":[91,108,135],"first":[94],"performs":[95],"small":[97],"but":[98],"random":[99],"number":[100],"iterations":[103],"before":[104],"switching":[105,117],"gradient":[109,136],"method.":[111],"show":[113],"time":[118],"properly":[120],"randomized,":[121],"LOKI":[122,145],"outperform":[126],"suboptimal":[128],"converge":[131],"faster":[132],"than":[133],"running":[134],"from":[137],"scratch.":[138],"Finally,":[139],"evaluate":[141],"experimentally":[146],"simulated":[149],"environments.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":4}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2019-07-30T00:00:00"}