{"id":"https://openalex.org/W309123013","doi":null,"title":"Reinforcement Learning with Human Feedback in Mountain Car","display_name":"Reinforcement Learning with Human Feedback in Mountain Car","publication_year":2011,"publication_date":"2011-03-20","ids":{"openalex":"https://openalex.org/W309123013","mag":"309123013"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.7616","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.7616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.media.mit.edu/%7Easetapen/papers/AAAISymp11-knox.pdf","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W309123013"],"child_works_count":0,"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/A5056649746","display_name":"W. Bradley Knox","orcid":"https://orcid.org/0000-0002-6006-9523","observed_orcids":["https://orcid.org/0000-0002-6006-9523"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Bradley Knox","raw_affiliation_strings":["University of Texas at Austin#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-6006-9523","affiliations":[{"raw_affiliation_string":"University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009616926","display_name":"Adam Setapen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Setapen","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X","observed_orcids":["https://orcid.org/0000-0002-6795-420X"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["University of Texas at Austin#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7141,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.73059947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"41"},"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/human-feedback","display_name":"human feedback","score":0.6570000052452087},{"id":"https://openalex.org/keywords/mountain-car-problem","display_name":"mountain car problem","score":0.7839999794960022},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5440000295639038},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6919999718666077},{"id":"https://openalex.org/keywords/human-in-the-loop-machine-learning","display_name":"human-in-the-loop learning","score":0.6470000147819519},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.5379999876022339}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9309482574462891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7327720522880554},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.7030899524688721},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6521897315979004},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6468703150749207},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6264538764953613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5251883268356323},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.47419124841690063},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41167110204696655},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3846191167831421},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3265121579170227},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12049105763435364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07869327068328857},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.7616","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.7616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.media.mit.edu/%7Easetapen/papers/AAAISymp11-knox.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.2360","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.2360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.adamsetapen.com/papers/11aaaisymp.pdf","raw_type":"text"},{"id":"mag:309123013","doi":null,"is_oa":false,"landing_page_url":"http://adamsetapen.com/papers/11aaaisymp.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420577","display_name":"National 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":"National Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W121023703","https://openalex.org/W1777239053","https://openalex.org/W2097113539","https://openalex.org/W2103048296","https://openalex.org/W2116157560","https://openalex.org/W2121863487","https://openalex.org/W2133990480","https://openalex.org/W2140584963","https://openalex.org/W2156869222","https://openalex.org/W2198041288"],"related_works":["https://openalex.org/W7095622576","https://openalex.org/W2294422333","https://openalex.org/W7124142776","https://openalex.org/W2116157560","https://openalex.org/W2545521674","https://openalex.org/W7124184780","https://openalex.org/W1979308911","https://openalex.org/W2186239216","https://openalex.org/W7124145248","https://openalex.org/W2110064869"],"abstract_inverted_index":{"As":[0],"computational":[1],"agents":[2,58],"are":[3],"increasingly":[4],"used":[5],"beyond":[6],"research":[7],"labs,":[8],"their":[9,14,23,37,140],"success":[10],"will":[11],"depend":[12],"on":[13,79,182],"ability":[15],"to":[16,22,40,161],"learn":[17],"new":[18],"skills":[19,33],"and":[20,68,107,114,135,138,154,188],"adapt":[21],"dynamic,":[24],"complex":[25],"environments.":[26],"If":[27],"human":[28,74,90,115,133,152],"users":[29],"\u2014":[30,34],"without":[31],"programming":[32],"can":[35,45,61],"transfer":[36],"task":[38],"knowledge":[39],"the":[41,55,83,89,95,122,176,179,183,189],"agents,":[42],"learning":[43,109,165],"rates":[44],"increase":[46],"dramatically,":[47],"reducing":[48],"costly":[49],"trials.":[50],"The":[51],"TAMER":[52,80],"framework":[53],"guides":[54],"design":[56],"of":[57,66,73,97,124,131,151,178],"whose":[59],"behavior":[60],"be":[62],"shaped":[63],"through":[64],"signals":[65],"approval":[67],"disapproval,":[69],"a":[70,101,146,163,171],"natural":[71],"form":[72],"feedback.":[75],"Whereas":[76],"early":[77],"work":[78],"assumed":[81],"that":[82,156],"agent\u2019s":[84],"only":[85],"feedback":[86],"was":[87],"from":[88,110],"teacher,":[91],"this":[92],"paper":[93],"considers":[94],"scenario":[96],"an":[98],"agent":[99],"within":[100],"Markov":[102],"Decision":[103],"Process":[104],"(MDP),":[105],"receiving":[106],"simultaneously":[108],"both":[111],"MDP":[112,119,136],"reward":[113,120,137],"reinforcement":[116,134,153,164],"signals.":[117],"Preserving":[118],"as":[121],"determinant":[123],"optimal":[125],"behavior,":[126],"we":[127],"test":[128],"two":[129],"methods":[130,144],"combining":[132],"analyze":[139],"respective":[141],"performances.":[142],"Both":[143],"create":[145],"predictive":[147],"model,":[148],"\u02c6":[149],"H,":[150],"use":[155],"model":[157],"in":[158],"different":[159],"ways":[160],"augment":[162],"(RL)":[166],"algorithm.":[167],"We":[168],"additionally":[169],"introduce":[170],"technique":[172],"for":[173],"appropriately":[174],"determining":[175],"magnitude":[177],"model\u2019s":[180],"influence":[181],"RL":[184],"algorithm":[185],"throughout":[186],"time":[187],"state":[190],"space.":[191]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}