{"id":"https://openalex.org/W197704362","doi":null,"title":"Real-Time Interactive Reinforcement Learning for Robots","display_name":"Real-Time Interactive Reinforcement Learning for Robots","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W197704362","mag":"197704362"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.512.6814","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.512.6814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aaai.org/Papers/Workshops/2005/WS-05-04/WS05-04-002.pdf","raw_type":"text"},"volume":null,"type":"conference-paper","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/A5066797327","display_name":"Andrea L. Thomaz","orcid":"https://orcid.org/0000-0002-3734-964X","observed_orcids":["https://orcid.org/0000-0002-3734-964X"]},"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":"Andrea L. Thomaz","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":"middle","author":{"id":"https://openalex.org/A5039553919","display_name":"Guy Hoffman","orcid":"https://orcid.org/0000-0002-0404-6159","observed_orcids":["https://orcid.org/0000-0002-0404-6159"]},"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":"Guy Hoffman","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0002-0404-6159","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108541589","display_name":"Cynthia Breazeal","orcid":"https://orcid.org/0000-0002-0587-2065","observed_orcids":["https://orcid.org/0000-0002-0587-2065"]},"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":"Cynthia Breazeal","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.7498,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.66165811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9789999723434448,"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":0.9789999723434448,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.008500000461935997,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.008299999870359898,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interactive-reinforcement-learning","display_name":"interactive reinforcement learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/assistive-robots","display_name":"assistive robots","score":0.972000002861023},{"id":"https://openalex.org/keywords/natural-interaction","display_name":"natural interaction","score":0.718999981880188},{"id":"https://openalex.org/keywords/robot-learning-from-humans","display_name":"robot learning from humans","score":0.5519999861717224}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6723785400390625},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6675937175750732},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6088350415229797},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5977801084518433},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5023977756500244},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.5015931129455566},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.48311400413513184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46168819069862366},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2012937366962433},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1133405864238739}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.512.6814","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.512.6814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aaai.org/Papers/Workshops/2005/WS-05-04/WS05-04-002.pdf","raw_type":"text"},{"id":"mag:197704362","doi":null,"is_oa":false,"landing_page_url":"https://www.aaai.org/Papers/Workshops/2005/WS-05-04/WS05-04-002.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"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":17,"referenced_works":["https://openalex.org/W111787296","https://openalex.org/W582695658","https://openalex.org/W1507591516","https://openalex.org/W1968729317","https://openalex.org/W1973674690","https://openalex.org/W1991564165","https://openalex.org/W2053000838","https://openalex.org/W2102000945","https://openalex.org/W2105888179","https://openalex.org/W2107726111","https://openalex.org/W2108157636","https://openalex.org/W2116372557","https://openalex.org/W2122410182","https://openalex.org/W2134067287","https://openalex.org/W2139612737","https://openalex.org/W2154342426","https://openalex.org/W2949071206"],"related_works":["https://openalex.org/W7100848873","https://openalex.org/W2903522344","https://openalex.org/W2559960928","https://openalex.org/W4365800577","https://openalex.org/W2996314008","https://openalex.org/W2588543665","https://openalex.org/W3128545355","https://openalex.org/W7100679092","https://openalex.org/W2045460262","https://openalex.org/W7095276754"],"abstract_inverted_index":{"It":[0],"is":[1],"our":[2,62],"goal":[3],"to":[4,45],"understand":[5],"the":[6,59],"role":[7],"real-time":[8],"human":[9],"in-teraction":[10],"can":[11],"play":[12],"in":[13],"machine":[14],"learning":[15],"algorithms":[16],"for":[17,32],"robots.":[18],"In":[19],"this":[20],"paper":[21],"we":[22],"present":[23],"Interactive":[24],"Reinforce-ment":[25],"Learning":[26],"(IRL)":[27],"as":[28],"a":[29],"plausible":[30],"approach":[31],"train-ing":[33],"human-centric":[34],"assistive":[35],"robots":[36],"by":[37],"natural":[38],"interac-tion.":[39],"We":[40],"describe":[41],"an":[42],"experimental":[43],"platform":[44],"study":[46],"IRL,":[47,52],"pose":[48],"questions":[49],"arising":[50],"from":[51],"and":[53],"discuss":[54],"ini-tial":[55],"observations":[56],"obtained":[57],"during":[58],"development":[60],"of":[61],"system.":[63]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}