{"id":"https://openalex.org/W2397581010","doi":null,"title":"Reinforcement learning from demonstration through shaping","display_name":"Reinforcement learning from demonstration through shaping","publication_year":2015,"publication_date":"2015-07-25","ids":{"openalex":"https://openalex.org/W2397581010","mag":"2397581010"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.723.9519","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.723.9519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ai.vub.ac.be/%7Etbrys/publications/Brys2015IJCAI.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5084002137","display_name":"Tim Brys","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tim Brys","raw_affiliation_strings":["Vrije Universiteit Br\u00fcssel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Br\u00fcssel","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014267939","display_name":"Anna Harutyunyan","orcid":"https://orcid.org/0000-0002-5418-113X","observed_orcids":["https://orcid.org/0000-0002-5418-113X"]},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Anna Harutyunyan","raw_affiliation_strings":["Vrije Universiteit Br\u00fcssel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Br\u00fcssel","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088717297","display_name":"Halit Bener Suay","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Halit Bener Suay","raw_affiliation_strings":["Worcester polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester polytechnic Institute","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033265891","display_name":"Sonia Chernova","orcid":"https://orcid.org/0000-0001-6320-0825","observed_orcids":["https://orcid.org/0000-0001-6320-0825"]},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sonia Chernova","raw_affiliation_strings":["Worcester polytechnic Institute"],"raw_orcid":"https://orcid.org/0000-0001-6320-0825","affiliations":[{"raw_affiliation_string":"Worcester polytechnic Institute","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070914351","display_name":"Matthew Edmund Taylor","orcid":"https://orcid.org/0000-0001-8946-0211","observed_orcids":["https://orcid.org/0000-0001-8946-0211"]},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew E. Taylor","raw_affiliation_strings":["washington state university"],"raw_orcid":"https://orcid.org/0000-0001-8946-0211","affiliations":[{"raw_affiliation_string":"washington state university","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064553018","display_name":"Ann Now\u00e9","orcid":"https://orcid.org/0000-0001-6346-4564","observed_orcids":["https://orcid.org/0000-0001-6346-4564"]},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ann Now\u00e9","raw_affiliation_strings":["Vrije Universiteit Br\u00fcssel"],"raw_orcid":"https://orcid.org/0000-0001-6346-4564","affiliations":[{"raw_affiliation_string":"Vrije Universiteit Br\u00fcssel","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.968,"has_fulltext":false,"cited_by_count":173,"citation_normalized_percentile":{"value":0.98944034,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3352","last_page":"3358"},"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/reinforcement-learning-from-demonstration","display_name":"reinforcement learning from demonstration","score":0.902999997138977},{"id":"https://openalex.org/keywords/reward-shaping","display_name":"reward shaping","score":0.996999979019165},{"id":"https://openalex.org/keywords/expert-demonstrations","display_name":"expert demonstrations","score":0.7229999899864197},{"id":"https://openalex.org/keywords/exploration-bias","display_name":"exploration bias","score":0.6370000243186951},{"id":"https://openalex.org/keywords/learning-speed","display_name":"learning speed","score":0.3840000033378601}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8585598468780518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480231523513794},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7155817747116089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5901332497596741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5106208920478821},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4831256568431854},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.41072097420692444},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1299365758895874},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"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":"pmh:oai:CiteSeerX.psu:10.1.1.723.9519","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.723.9519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ai.vub.ac.be/%7Etbrys/publications/Brys2015IJCAI.pdf","raw_type":"text"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:132022","doi":null,"is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/reinforcement-learning-from-demonstration-through-shaping(afae560f-e9c4-462a-8aef-8d82f80fd0e7).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"},{"id":"mag:2397581010","doi":null,"is_oa":false,"landing_page_url":"http://irll.eecs.wsu.edu/wp-content/papercite-data/pdf/2015ijcai-brys.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419142","display_name":"International Conference on 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":"International Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W46130386","https://openalex.org/W121023703","https://openalex.org/W1511887321","https://openalex.org/W1515851193","https://openalex.org/W1531166221","https://openalex.org/W1540685400","https://openalex.org/W1777239053","https://openalex.org/W1977546238","https://openalex.org/W1986014385","https://openalex.org/W1996625075","https://openalex.org/W1996847178","https://openalex.org/W2001898186","https://openalex.org/W2097381042","https://openalex.org/W2103285838","https://openalex.org/W2105486945","https://openalex.org/W2113913482","https://openalex.org/W2115668428","https://openalex.org/W2116157560","https://openalex.org/W2121863487","https://openalex.org/W2133040789","https://openalex.org/W2137375617","https://openalex.org/W2147750403","https://openalex.org/W2154342426","https://openalex.org/W2156578004","https://openalex.org/W2164419340","https://openalex.org/W2250649096","https://openalex.org/W3127231893"],"related_works":["https://openalex.org/W158183001","https://openalex.org/W7124175820","https://openalex.org/W2808546214","https://openalex.org/W7096434988","https://openalex.org/W2915657644","https://openalex.org/W1769460679","https://openalex.org/W7124275396","https://openalex.org/W3037916989","https://openalex.org/W7099037337","https://openalex.org/W2189559150"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,5,25,81,129,176],"describes":[2],"how":[3],"a":[4,47,65,134],"agent":[6,45,61],"can":[7,88],"achieve":[8],"optimal":[9],"behaviour":[10],"based":[11],"on":[12],"in-teractions":[13],"with":[14,62],"its":[15],"environment":[16],"and":[17,97,121,172],"reward":[18,137],"feed-back.":[19],"A":[20],"limiting":[21],"factor":[22],"in":[23,28],"reinforcement":[24,119],"as":[26],"employed":[27],"artificial":[29],"intelligence":[30],"is":[31,55,84,165],"the":[32,44,60,78,92,95,99,107,114,178],"need":[33],"for":[34,91],"an":[35,56,149],"often":[36],"prohibitively":[37],"large":[38],"number":[39],"of":[40,50,77,80,94,109,170],"environ-ment":[41],"samples":[42],"before":[43],"reaches":[46],"desirable":[48],"level":[49],"performance.":[51],"Learning":[52],"from":[53,68,82],"demonstra-tion":[54],"approach":[57,140],"that":[58,85,158],"provides":[59],"demonstrations":[63,124],"by":[64,118,130],"supposed":[66],"expert,":[67],"which":[69],"it":[70],"should":[71],"derive":[72],"suitable":[73],"behaviour.":[74],"Yet,":[75],"one":[76],"challenges":[79],"demonstration":[83,153],"no":[86],"guarantees":[87,116],"be":[89],"provided":[90,117],"qual-ity":[93],"demonstrations,":[96,164],"thus":[98],"learned":[100],"be-havior.":[101],"In":[102],"this":[103,128,159],"paper,":[104],"we":[105],"investigate":[106],"intersec-tion":[108],"these":[110],"two":[111],"approaches,":[112],"leveraging":[113],"theo-retical":[115],"learn-ing,":[120],"using":[122],"expert":[123],"to":[125,143],"speed":[126],"up":[127],"biasing":[131],"exploration":[132],"through":[133],"pro-cess":[135],"called":[136],"shaping.":[138],"This":[139],"allows":[141],"us":[142],"leverage":[144],"human":[145],"input":[146],"without":[147],"making":[148],"er-roneous":[150],"assumption":[151],"regarding":[152],"op-timality.":[154],"We":[155],"show":[156],"experimentally":[157],"ap-proach":[160],"requires":[161],"significantly":[162],"fewer":[163],"more":[166],"robust":[167],"against":[168],"suboptimality":[169],"demonstra-tions,":[171],"achieves":[173],"much":[174],"faster":[175],"than":[177],"recently":[179],"developed":[180],"HAT":[181],"algorithm.":[182],"1":[183]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}