{"id":"https://openalex.org/W2784831250","doi":"https://doi.org/10.1109/icra.2018.8462977","title":"Cross-Domain Transfer in Reinforcement Learning Using Target Apprentice","display_name":"Cross-Domain Transfer in Reinforcement Learning Using Target Apprentice","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2784831250","doi":"https://doi.org/10.1109/icra.2018.8462977","mag":"2784831250"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2018.8462977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8462977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1801.06920","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065683918","display_name":"Girish Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Girish Joshi","raw_affiliation_strings":["Department of Agriculture and Biological Engineering and Coordinated Science Lab, University of Illinois, Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Agriculture and Biological Engineering and Coordinated Science Lab, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073739058","display_name":"Girish Chowdhary","orcid":"https://orcid.org/0000-0002-4657-307X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Girish Chowdhary","raw_affiliation_strings":["Department of Agriculture and Biological Engineering and Coordinated Science Lab, University of Illinois, Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Agriculture and Biological Engineering and Coordinated Science Lab, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065683918"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.8462,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79611237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7525","last_page":"7532"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983000159263611,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8673218488693237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.793839693069458},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7891223430633545},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7335513830184937},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5965662598609924},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5471356511116028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5153388381004333},{"id":"https://openalex.org/keywords/apprenticeship","display_name":"Apprenticeship","score":0.49551641941070557},{"id":"https://openalex.org/keywords/negative-transfer","display_name":"Negative transfer","score":0.4832054376602173},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4829770624637604},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.48257747292518616},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.461794376373291},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4556692838668823},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4372686743736267},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07174801826477051},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06837758421897888}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8673218488693237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.793839693069458},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7891223430633545},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7335513830184937},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5965662598609924},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5471356511116028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5153388381004333},{"id":"https://openalex.org/C107806365","wikidata":"https://www.wikidata.org/wiki/Q253567","display_name":"Apprenticeship","level":2,"score":0.49551641941070557},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.4832054376602173},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4829770624637604},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.48257747292518616},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.461794376373291},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4556692838668823},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4372686743736267},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07174801826477051},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06837758421897888},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra.2018.8462977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8462977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1801.06920","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1801.06920","pdf_url":"https://arxiv.org/pdf/1801.06920","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:2784831250","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1801.06920","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1801.06920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1801.06920","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1801.06920","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1801.06920","pdf_url":"https://arxiv.org/pdf/1801.06920","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G7084746226","display_name":null,"funder_award_id":"FA9550-15-1-0146","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2784831250.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W64698994","https://openalex.org/W110451278","https://openalex.org/W1492014007","https://openalex.org/W1499408472","https://openalex.org/W1848094219","https://openalex.org/W1991753499","https://openalex.org/W1996625075","https://openalex.org/W2019324135","https://openalex.org/W2078676277","https://openalex.org/W2097381042","https://openalex.org/W2098723043","https://openalex.org/W2106953752","https://openalex.org/W2127107099","https://openalex.org/W2128905965","https://openalex.org/W2133040789","https://openalex.org/W2145339207","https://openalex.org/W2156493855","https://openalex.org/W2164114810","https://openalex.org/W6602657573","https://openalex.org/W6604483558","https://openalex.org/W6638853687","https://openalex.org/W6674600207","https://openalex.org/W6674887642","https://openalex.org/W6676297359","https://openalex.org/W6679426499","https://openalex.org/W6679818365","https://openalex.org/W6682768811","https://openalex.org/W6683204974","https://openalex.org/W6684205842"],"related_works":["https://openalex.org/W2962817122","https://openalex.org/W3037277520","https://openalex.org/W3209208698","https://openalex.org/W3167613675","https://openalex.org/W1481405077","https://openalex.org/W66188587","https://openalex.org/W110451278","https://openalex.org/W1569756368","https://openalex.org/W1696410204","https://openalex.org/W3118694267","https://openalex.org/W2056107474","https://openalex.org/W2945090640","https://openalex.org/W3037023372","https://openalex.org/W2289410116","https://openalex.org/W24272225","https://openalex.org/W3120444854","https://openalex.org/W2398490066","https://openalex.org/W2799245749","https://openalex.org/W2403765497","https://openalex.org/W3029221344"],"abstract_inverted_index":{"In":[0],"this":[1,105],"paper,":[2],"we":[3,32],"present":[4],"a":[5,53],"new":[6,100],"approach":[7],"to":[8,34,97,108,122],"transfer":[9,19],"in":[10,43,61,88,112],"Reinforcement":[11],"Learning":[12],"(RL)":[13],"for":[14,69],"cross-domain":[15],"tasks.":[16,101],"Unlike,":[17],"available":[18],"approaches,":[20],"where":[21],"target":[22,62,74,119,123],"task":[23,56,120],"learning":[24,29,121],"is":[25,87],"accelerated":[26],"through":[27],"initialized":[28],"from":[30,52],"source,":[31],"propose":[33],"adapt":[35],"and":[36,75],"reuse":[37],"the":[38,44,49,70,76,83,90,99,113],"optimal":[39,50,60],"source":[40,55],"policy":[41,51,67,85],"directly":[42],"related":[45,54,93],"domains.":[46],"We":[47,102],"show":[48],"can":[57],"be":[58],"near":[59],"domain":[63],"provided":[64],"an":[65],"adaptive":[66],"accounts":[68],"model":[71],"error":[72],"between":[73],"projected":[77],"source.":[78],"A":[79],"significant":[80],"advantage":[81],"of":[82,118],"proposed":[84],"augmentation":[86],"generalizing":[89],"policies":[91],"across":[92],"domains":[94],"without":[95],"having":[96],"re-Iearn":[98],"demonstrate":[103],"that,":[104],"architecture":[106],"leads":[107],"better":[109],"sample":[110,116],"efficiency":[111],"transfer,":[114],"reducing":[115],"complexity":[117],"apprentice":[124],"learning.":[125]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
