{"id":"https://openalex.org/W3174881493","doi":"https://doi.org/10.1145/3461778.3462135","title":"A Survey of Collaborative Reinforcement Learning: Interactive Methods and Design Patterns","display_name":"A Survey of Collaborative Reinforcement Learning: Interactive Methods and Design Patterns","publication_year":2021,"publication_date":"2021-06-28","ids":{"openalex":"https://openalex.org/W3174881493","doi":"https://doi.org/10.1145/3461778.3462135","mag":"3174881493"},"language":"en","primary_location":{"id":"doi:10.1145/3461778.3462135","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461778.3462135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Designing Interactive Systems Conference 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://durham-repository.worktribe.com/output/1140738","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052703378","display_name":"Zhaoxing Li","orcid":"https://orcid.org/0000-0003-3560-3461"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhaoxing Li","raw_affiliation_strings":["Durham university Department of Computer Science, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham university Department of Computer Science, United Kingdom","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427516","display_name":"Lei Shi","orcid":"https://orcid.org/0000-0001-7119-3207"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lei Shi","raw_affiliation_strings":["Durham University, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University, United Kingdom","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034125179","display_name":"Alexandra I. Cristea","orcid":"https://orcid.org/0000-0002-1454-8822"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexandra I. Cristea","raw_affiliation_strings":["Durham University, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University, United Kingdom","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003657349","display_name":"Yunzhan Zhou","orcid":"https://orcid.org/0000-0003-1676-0015"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yunzhan Zhou","raw_affiliation_strings":["Durham university Department of Computer Science, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham university Department of Computer Science, United Kingdom","institution_ids":["https://openalex.org/I190082696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5393,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.85964263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1579","last_page":"1590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9307000041007996,"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":0.9307000041007996,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7865982055664062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7338817119598389},{"id":"https://openalex.org/keywords/collaborative-learning","display_name":"Collaborative learning","score":0.6473106145858765},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5046228170394897},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.45423856377601624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42784208059310913},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33206668496131897},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.2204264998435974}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7865982055664062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7338817119598389},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.6473106145858765},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5046228170394897},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45423856377601624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42784208059310913},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33206668496131897},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2204264998435974},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3461778.3462135","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461778.3462135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Designing Interactive Systems Conference 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:dro.dur.ac.uk.OAI2:33292","is_oa":false,"landing_page_url":"http://dro.dur.ac.uk/33292/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196258","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"ACM Designing Interactive Systems (DIS), Virtual, 28 Jun - 02 Jul 2021 [Conference proceedings]","raw_type":"Conference item"},{"id":"pmh:oai:durham-repository.worktribe.com:1140738","is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/1140738","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},{"id":"pmh:oai:eprints.soton.ac.uk:486533","is_oa":false,"landing_page_url":"https://eprints.soton.ac.uk/486533/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":{"id":"pmh:oai:durham-repository.worktribe.com:1140738","is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/1140738","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W197704362","https://openalex.org/W1494352995","https://openalex.org/W1501005121","https://openalex.org/W1537222736","https://openalex.org/W1587826671","https://openalex.org/W1603301045","https://openalex.org/W1604034318","https://openalex.org/W1757796397","https://openalex.org/W1845972764","https://openalex.org/W1977253332","https://openalex.org/W1977655452","https://openalex.org/W1982629367","https://openalex.org/W1986014385","https://openalex.org/W1989386832","https://openalex.org/W2007339694","https://openalex.org/W2011024242","https://openalex.org/W2028626340","https://openalex.org/W2050399307","https://openalex.org/W2062525454","https://openalex.org/W2098441518","https://openalex.org/W2104308387","https://openalex.org/W2114864106","https://openalex.org/W2118659391","https://openalex.org/W2118756286","https://openalex.org/W2121110499","https://openalex.org/W2121863487","https://openalex.org/W2131600418","https://openalex.org/W2132401613","https://openalex.org/W2137375617","https://openalex.org/W2140584963","https://openalex.org/W2148166693","https://openalex.org/W2156869222","https://openalex.org/W2164414043","https://openalex.org/W2261254692","https://openalex.org/W2395263189","https://openalex.org/W2522489477","https://openalex.org/W2560862806","https://openalex.org/W2565110810","https://openalex.org/W2787259794","https://openalex.org/W2800934671","https://openalex.org/W2808546214","https://openalex.org/W2883364792","https://openalex.org/W2883535494","https://openalex.org/W2885518439","https://openalex.org/W2887029808","https://openalex.org/W2890809352","https://openalex.org/W2891503716","https://openalex.org/W2896215772","https://openalex.org/W2941665215","https://openalex.org/W2942182378","https://openalex.org/W2944766483","https://openalex.org/W2945022240","https://openalex.org/W2961759237","https://openalex.org/W2963489214","https://openalex.org/W2964654516","https://openalex.org/W2998594699","https://openalex.org/W3003931103","https://openalex.org/W3005891386","https://openalex.org/W3015342956","https://openalex.org/W3022194887","https://openalex.org/W3025747022","https://openalex.org/W3039116038","https://openalex.org/W3097884524","https://openalex.org/W4231358230","https://openalex.org/W4239082564","https://openalex.org/W4285719527","https://openalex.org/W4366961264"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Recently,":[0],"methods":[1,43,65,139],"enabling":[2],"humans":[3,147],"and":[4,51,57,61,73,81,101,135,148],"Artificial":[5],"Intelligent":[6],"(AI)":[7],"agents":[8],"to":[9,128,131],"collaborate":[10],"towards":[11,119],"improving":[12,102],"the":[13,68,71,74,113,143],"efficiency":[14],"of":[15,66,70,122,146],"Reinforcement":[16,22],"Learning":[17,23],"-":[18,25],"also":[19],"called":[20],"Collaborative":[21],"(CRL)":[24],"have":[26],"been":[27],"receiving":[28],"increasing":[29],"attention.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,76,87,107],"provide":[35,88],"a":[36,89,95,117],"long-term,":[37],"in-depth":[38],"survey,":[39],"investigating":[40],"human-AI":[41,52,123,137],"collaborative":[42,53,138],"based":[44],"on":[45],"both":[46,67],"interactive":[47],"reinforcement":[48],"learning":[49],"algorithms":[50],"frameworks,":[54],"between":[55],"2011":[56],"2020.":[58],"We":[59],"elucidate":[60],"discuss":[62],"synergistic":[63],"analysis":[64],"growth":[69],"field":[72],"state-of-the-art;":[75],"suggest":[77],"novel":[78],"technical":[79],"directions":[80],"new":[82,90,103],"collaboration":[83],"design":[84],"ideas.":[85],"Specifically,":[86],"CRL":[91,104,110],"classification":[92],"taxonomy,":[93],"as":[94],"systematic":[96],"modelling":[97],"tool":[98],"for":[99],"selecting":[100],"designs.":[105],"Furthermore,":[106],"propose":[108],"generic":[109],"challenges":[111],"providing":[112],"research":[114],"community":[115],"with":[116],"guide":[118],"effective":[120],"implementation":[121],"collaboration.":[124],"The":[125],"aim":[126],"is":[127],"empower":[129],"researchers":[130],"develop":[132],"more":[133],"efficient":[134],"natural":[136],"that":[140],"could":[141],"utilise":[142],"different":[144],"strengths":[145],"AI.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}