{"id":"https://openalex.org/W2491675558","doi":"https://doi.org/10.5555/2936924.2936988","title":"Learning from Demonstration for Shaping through Inverse Reinforcement Learning","display_name":"Learning from Demonstration for Shaping through Inverse Reinforcement Learning","publication_year":2016,"publication_date":"2016-05-09","ids":{"openalex":"https://openalex.org/W2491675558","doi":"https://doi.org/10.5555/2936924.2936988","mag":"2491675558"},"language":"en","primary_location":{"id":"pmh:oai:vubissmart:VUBISSMART:2000:135308","doi":null,"is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/learning-from-demonstration-for-shaping-through-inverse-reinforcement-learning(6a0730d7-948d-454f-8e09-273a20320a8f).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"},"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/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, Worcester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","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 Brussel, Brussels, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Brussel, Brussels, USA","institution_ids":["https://openalex.org/I13469542"]}]},{"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, Pullman, WA USA"],"raw_orcid":"https://orcid.org/0000-0001-8946-0211","affiliations":[{"raw_affiliation_string":"Washington State University, Pullman, WA USA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"last","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/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":"Sonia Chernova","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA (USA)"],"raw_orcid":"https://orcid.org/0000-0001-6320-0825","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA (USA)","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4221,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.96986477,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"429","last_page":"437"},"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":0.8220000267028809},{"id":"https://openalex.org/keywords/inverse-reinforcement-learning","display_name":"inverse reinforcement learning","score":0.9490000009536743},{"id":"https://openalex.org/keywords/reward-shaping","display_name":"reward shaping","score":0.9449999928474426},{"id":"https://openalex.org/keywords/potential-based-reward-shaping","display_name":"potential-based reward shaping","score":0.9629999995231628},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.7289999723434448},{"id":"https://openalex.org/keywords/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.8690000176429749},{"id":"https://openalex.org/keywords/episodic-reinforcement-learning","display_name":"episodic reinforcement learning","score":0.7580000162124634},{"id":"https://openalex.org/keywords/maze-navigation","display_name":"maze navigation","score":0.5410000085830688}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.898151159286499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765162467956543},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6946250200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6168007850646973},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6021571159362793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5516442656517029},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5164099335670471},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4783629775047302},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4773573875427246},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.43789321184158325},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4258756935596466},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16250592470169067},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08258244395256042},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08019807934761047},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:vubissmart:VUBISSMART:2000:135308","doi":null,"is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/learning-from-demonstration-for-shaping-through-inverse-reinforcement-learning(6a0730d7-948d-454f-8e09-273a20320a8f).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:2491675558","doi":"https://doi.org/10.5555/2936924.2936988","is_oa":false,"landing_page_url":"http://ai.vub.ac.be/~tbrys/publications/Suay2016AAMAS.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"Adaptive Agents and Multi-Agents Systems","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":26,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1569296262","https://openalex.org/W1583833196","https://openalex.org/W1777239053","https://openalex.org/W1801976851","https://openalex.org/W1854866626","https://openalex.org/W1996847178","https://openalex.org/W1999874108","https://openalex.org/W2009435671","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2115668428","https://openalex.org/W2116774898","https://openalex.org/W2119567691","https://openalex.org/W2133068870","https://openalex.org/W2137375617","https://openalex.org/W2148112459","https://openalex.org/W2164114810","https://openalex.org/W2164419340","https://openalex.org/W2169498096","https://openalex.org/W2171302338","https://openalex.org/W2202549229","https://openalex.org/W2218252352","https://openalex.org/W2397581010","https://openalex.org/W3139377883","https://openalex.org/W7124149817"],"related_works":["https://openalex.org/W2397581010","https://openalex.org/W2008491003","https://openalex.org/W3095695436","https://openalex.org/W2808546214","https://openalex.org/W7124284865","https://openalex.org/W2161009228","https://openalex.org/W2939047085","https://openalex.org/W1999874108","https://openalex.org/W7214736981","https://openalex.org/W158183001"],"abstract_inverted_index":{"Model-free":[0],"episodic":[1],"reinforcement":[2,60,84,142],"learning":[3,61,85,143,159],"problems":[4],"define":[5],"the":[6,18,28,34,75,89,108,126,134,154],"environment":[7],"reward":[8,47,94],"with":[9,37,46,64],"functions":[10],"that":[11,150],"often":[12],"provide":[13],"only":[14],"sparse":[15],"information":[16],"throughout":[17],"task.":[19],"Consequently,":[20],"agents":[21],"are":[22],"not":[23],"given":[24],"enough":[25],"feedback":[26],"about":[27],"fitness":[29],"of":[30,110,117,136],"their":[31],"actions":[32],"until":[33],"task":[35],"ends":[36],"success":[38],"or":[39],"failure.":[40],"Previous":[41],"work":[42],"addresses":[43],"this":[44,50],"problem":[45],"shaping.":[48,95],"In":[49],"paper":[51],"we":[52,70,87,113],"introduce":[53],"a":[54,65,79,120],"novel":[55],"approach":[56,97,112,152],"to":[57,77,102,139],"improve":[58],"model-free":[59,99],"agents'":[62],"performance":[63,135],"three":[66],"step":[67],"approach.":[68],"Specifically,":[69],"collect":[71],"demonstration":[72,145],"data,":[73],"use":[74,88],"data":[76],"recover":[78],"linear":[80],"function":[81,91],"using":[82],"inverse":[83],"and":[86,100,125,161],"recovered":[90],"for":[92],"potential-based":[93],"Our":[96,147],"is":[98],"scalable":[101],"high":[103],"dimensional":[104,122,128],"domains.":[105],"To":[106],"show":[107,149],"scalability":[109],"our":[111,137,151],"present":[114],"two":[115,121],"sets":[116],"experiments":[118,148],"in":[119,156],"Maze":[123],"domain,":[124],"27":[127],"Mario":[129],"AI":[130],"domain.":[131],"We":[132],"compare":[133],"algorithm":[138],"previously":[140],"introduced":[141],"from":[144],"algorithms.":[146],"outperforms":[153],"state-of-the-art":[155],"cumulative":[157],"reward,":[158],"rate":[160],"asymptotic":[162],"performance.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-08-23T00:00:00"}