{"id":"https://openalex.org/W3178075461","doi":"https://doi.org/10.1145/3453892.3454004","title":"Accelerating Human-Agent Collaborative Reinforcement Learning","display_name":"Accelerating Human-Agent Collaborative Reinforcement Learning","publication_year":2021,"publication_date":"2021-06-29","ids":{"openalex":"https://openalex.org/W3178075461","doi":"https://doi.org/10.1145/3453892.3454004","mag":"3178075461"},"language":"en","primary_location":{"id":"doi:10.1145/3453892.3454004","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3453892.3454004","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3453892.3454004","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th PErvasive Technologies Related to Assistive Environments Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3453892.3454004","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064630658","display_name":"Fotios Lygerakis","orcid":"https://orcid.org/0000-0001-8044-3511"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fotios Lygerakis","raw_affiliation_strings":["University of Texas at Arlington National Center for Scientific Reseaarch Demokritos, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington National Center for Scientific Reseaarch Demokritos, United States","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031672975","display_name":"Maria Dagioglou","orcid":"https://orcid.org/0000-0002-3357-2844"},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Maria Dagioglou","raw_affiliation_strings":["National Centre for Scientific Research Demokritos, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Centre for Scientific Research Demokritos, Greece","institution_ids":["https://openalex.org/I203474044"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018887199","display_name":"Vangelis Karkaletsis","orcid":"https://orcid.org/0000-0002-7062-9424"},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vangelis Karkaletsis","raw_affiliation_strings":["National Centre for Scientific Research Demokritos, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Centre for Scientific Research Demokritos, Greece","institution_ids":["https://openalex.org/I203474044"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"90","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9803000092506409,"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"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9585000276565552,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8739321231842041},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7235305905342102},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7103544473648071},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5445071458816528},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5208714008331299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4901619851589203},{"id":"https://openalex.org/keywords/collaborative-learning","display_name":"Collaborative learning","score":0.47843530774116516},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.4669177532196045},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4576394557952881},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.20634672045707703},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07031145691871643}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8739321231842041},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7235305905342102},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7103544473648071},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5445071458816528},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5208714008331299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4901619851589203},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.47843530774116516},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.4669177532196045},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4576394557952881},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.20634672045707703},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07031145691871643},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3453892.3454004","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3453892.3454004","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3453892.3454004","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th PErvasive Technologies Related to Assistive Environments Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3453892.3454004","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3453892.3454004","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3453892.3454004","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th PErvasive Technologies Related to Assistive Environments Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322565","display_name":"Stavros Niarchos Foundation","ror":"https://ror.org/0210rze73"},{"id":"https://openalex.org/F4320335042","display_name":"National Council for Scientific Research","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3178075461.pdf","grobid_xml":"https://content.openalex.org/works/W3178075461.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2110064869","https://openalex.org/W2617916659","https://openalex.org/W2760057500","https://openalex.org/W2781726626","https://openalex.org/W2789905221","https://openalex.org/W2834877435","https://openalex.org/W2904246096","https://openalex.org/W2964263543","https://openalex.org/W2981037657","https://openalex.org/W3009952864","https://openalex.org/W3035794106","https://openalex.org/W4287829732"],"related_works":["https://openalex.org/W2348837382","https://openalex.org/W746329893","https://openalex.org/W4205872570","https://openalex.org/W4245971243","https://openalex.org/W1922805944","https://openalex.org/W4253588120","https://openalex.org/W2383732295","https://openalex.org/W2942717012","https://openalex.org/W4248716494","https://openalex.org/W2162226802"],"abstract_inverted_index":{"In":[0],"domains":[1],"such":[2],"as":[3],"Human-Robot":[4],"Collaboration":[5],"artificial":[6],"agents":[7],"must":[8],"be":[9],"able":[10],"to":[11],"support":[12],"mutual":[13],"adaptation":[14],"and":[15,41,49],"learning.":[16],"Towards":[17],"this":[18],"direction,":[19],"we":[20],"use":[21],"a":[22,28,61],"discrete":[23],"Soft":[24],"Actor-Critic":[25],"agent":[26],"on":[27],"real-time":[29],"collaborative":[30],"game":[31,47],"with":[32],"humans.":[33],"We":[34],"examine":[35],"how":[36],"different":[37],"allocations":[38],"of":[39,60,64],"on-line":[40],"off-line":[42,65],"gradient":[43],"updates":[44],"impact":[45],"the":[46,50],"performance":[48],"total":[51],"training":[52,72],"time.":[53],"Our":[54],"results":[55],"suggest":[56],"that":[57],"early":[58],"allocation":[59],"high":[62],"number":[63],"g/u":[66],"can":[67],"accelerate":[68],"learning":[69],"while":[70],"shortening":[71],"duration.":[73]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}