{"id":"https://openalex.org/W2129659607","doi":"https://doi.org/10.1109/roman.2011.6005223","title":"Effect of human guidance and state space size on Interactive Reinforcement Learning","display_name":"Effect of human guidance and state space size on Interactive Reinforcement Learning","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2129659607","doi":"https://doi.org/10.1109/roman.2011.6005223","mag":"2129659607"},"language":"en","primary_location":{"id":"doi:10.1109/roman.2011.6005223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2011.6005223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 RO-MAN","raw_type":"proceedings-article"},"type":"article","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/A5088717297","display_name":"Halit Bener Suay","orcid":null},"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":true,"raw_author_name":"Halit Bener Suay","raw_affiliation_strings":["Robotics Engineering Program, Worcester Polytechnic Institute, Worcester, MA, USA","Robotics Engineering Program, Worcester Polytechnic Institute, 100 Institute Rd, MA 01609, USA"],"affiliations":[{"raw_affiliation_string":"Robotics Engineering Program, Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Robotics Engineering Program, Worcester Polytechnic Institute, 100 Institute Rd, MA 01609, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033265891","display_name":"Sonia Chernova","orcid":"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":["Robotics Engineering Program, Worcester Polytechnic Institute, Worcester, MA, USA","Robotics Engineering Program, Worcester Polytechnic Institute, 100 Institute Rd, MA 01609, USA"],"affiliations":[{"raw_affiliation_string":"Robotics Engineering Program, Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Robotics Engineering Program, Worcester Polytechnic Institute, 100 Institute Rd, MA 01609, USA","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088717297"],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":4.3857,"has_fulltext":false,"cited_by_count":118,"citation_normalized_percentile":{"value":0.94562466,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9843000173568726,"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/T12288","display_name":"Optimization and Search Problems","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.920859694480896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6938059329986572},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5751082301139832},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5254520773887634},{"id":"https://openalex.org/keywords/interactive-learning","display_name":"Interactive Learning","score":0.522181510925293},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5086063146591187},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5076483488082886},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.477964848279953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47523048520088196},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.47194474935531616},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43754512071609497},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.42032167315483093},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.4200247526168823},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41502898931503296},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30090606212615967},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.22157150506973267},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.1977158784866333},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14920687675476074}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.920859694480896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6938059329986572},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5751082301139832},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5254520773887634},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.522181510925293},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5086063146591187},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5076483488082886},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.477964848279953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47523048520088196},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.47194474935531616},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43754512071609497},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.42032167315483093},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4200247526168823},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41502898931503296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30090606212615967},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.22157150506973267},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.1977158784866333},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14920687675476074},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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":2,"locations":[{"id":"doi:10.1109/roman.2011.6005223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2011.6005223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 RO-MAN","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.654.3785","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.654.3785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.wpi.edu/%7Ebenersuay/publications/suay_roman2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W121023703","https://openalex.org/W170770739","https://openalex.org/W1492518272","https://openalex.org/W1521468904","https://openalex.org/W1533162639","https://openalex.org/W1585546346","https://openalex.org/W1677409904","https://openalex.org/W1949804828","https://openalex.org/W1986014385","https://openalex.org/W2041367235","https://openalex.org/W2104308387","https://openalex.org/W2114882146","https://openalex.org/W2119567691","https://openalex.org/W2119605622","https://openalex.org/W2121863487","https://openalex.org/W2132504164","https://openalex.org/W2153667689","https://openalex.org/W2154018708","https://openalex.org/W2156869222","https://openalex.org/W2162768030","https://openalex.org/W2334782222","https://openalex.org/W2336416123","https://openalex.org/W4214717370","https://openalex.org/W6629536611","https://openalex.org/W6635147684","https://openalex.org/W6684100231"],"related_works":["https://openalex.org/W2544716473","https://openalex.org/W2126211886","https://openalex.org/W2171128163","https://openalex.org/W2331496072","https://openalex.org/W1974960581","https://openalex.org/W1988329011","https://openalex.org/W4235346315","https://openalex.org/W2138277950","https://openalex.org/W2999580272","https://openalex.org/W2171010636"],"abstract_inverted_index":{"The":[0],"Interactive":[1,48,72,106],"Reinforcement":[2,49,73,107],"Learning":[3,50,74,108],"algorithm":[4],"enables":[5],"a":[6,11,110],"human":[7],"user":[8,40],"to":[9,18,24,104,109],"train":[10],"robot":[12],"by":[13,57],"providing":[14],"rewards":[15],"in":[16,75],"response":[17],"past":[19],"actions":[20],"and":[21,91,113,122],"anticipatory":[22],"guidance":[23,41,90,116],"guide":[25],"the":[26,43,53,59,63,68,86,119],"selection":[27],"of":[28,61,71],"future":[29],"actions.":[30],"Past":[31],"work":[32],"with":[33,128],"software":[34],"agents":[35],"has":[36],"shown":[37],"that":[38,84,88,115,123],"incorporating":[39],"into":[42],"policy":[44,54,97],"learning":[45,55,98,120],"process":[46],"through":[47],"significantly":[51,117],"improves":[52],"time":[56],"reducing":[58],"number":[60],"states":[62],"agent":[64],"explores.":[65],"We":[66,79,100],"present":[67],"first":[69],"study":[70,85],"real-world":[76,111],"robotic":[77],"systems.":[78],"report":[80],"on":[81,96],"four":[82],"experiments":[83],"effects":[87,126],"teacher":[89],"state":[92,129],"space":[93,130],"size":[94],"have":[95],"performance.":[99],"discuss":[101],"modifications":[102],"made":[103],"apply":[105],"system":[112],"show":[114],"reduces":[118],"rate,":[121],"its":[124],"positive":[125],"increase":[127],"size.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}