{"id":"https://openalex.org/W3039116038","doi":"https://doi.org/10.1145/3357236.3395525","title":"A Survey on Interactive Reinforcement Learning","display_name":"A Survey on Interactive Reinforcement Learning","publication_year":2020,"publication_date":"2020-07-03","ids":{"openalex":"https://openalex.org/W3039116038","doi":"https://doi.org/10.1145/3357236.3395525","mag":"3039116038"},"language":"en","primary_location":{"id":"doi:10.1145/3357236.3395525","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357236.3395525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM Designing Interactive Systems Conference","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/A5028316887","display_name":"Christian Arzate Cruz","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Christian Arzate Cruz","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102743150","display_name":"Takeo Igarashi","orcid":"https://orcid.org/0000-0002-5495-6441"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeo Igarashi","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028316887"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":5.9533,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.96929497,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1195","last_page":"1209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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":0.9976999759674072,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9555000066757202,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9541000127792358,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8178603649139404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.785930335521698},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.7153088450431824},{"id":"https://openalex.org/keywords/interactive-learning","display_name":"Interactive Learning","score":0.5681551694869995},{"id":"https://openalex.org/keywords/interaction-design","display_name":"Interaction design","score":0.47635388374328613},{"id":"https://openalex.org/keywords/interactive-design","display_name":"Interactive design","score":0.4531243145465851},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3264133930206299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2120157778263092}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8178603649139404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.785930335521698},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.7153088450431824},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.5681551694869995},{"id":"https://openalex.org/C13854087","wikidata":"https://www.wikidata.org/wiki/Q1061656","display_name":"Interaction design","level":2,"score":0.47635388374328613},{"id":"https://openalex.org/C86297840","wikidata":"https://www.wikidata.org/wiki/Q6045397","display_name":"Interactive design","level":2,"score":0.4531243145465851},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3264133930206299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2120157778263092}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3357236.3395525","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357236.3395525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM Designing Interactive Systems Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W8222043","https://openalex.org/W179992386","https://openalex.org/W1501005121","https://openalex.org/W1536323281","https://openalex.org/W1569296262","https://openalex.org/W1591803298","https://openalex.org/W1655830068","https://openalex.org/W1777239053","https://openalex.org/W1845972764","https://openalex.org/W1921016406","https://openalex.org/W1999874108","https://openalex.org/W2003238113","https://openalex.org/W2027106130","https://openalex.org/W2062525454","https://openalex.org/W2094387729","https://openalex.org/W2098441518","https://openalex.org/W2098774185","https://openalex.org/W2104759087","https://openalex.org/W2106930353","https://openalex.org/W2115668428","https://openalex.org/W2116671302","https://openalex.org/W2121110499","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2133950705","https://openalex.org/W2151074445","https://openalex.org/W2156869222","https://openalex.org/W2164114810","https://openalex.org/W2300445845","https://openalex.org/W2395263189","https://openalex.org/W2515496004","https://openalex.org/W2539402368","https://openalex.org/W2540439332","https://openalex.org/W2559960928","https://openalex.org/W2560674852","https://openalex.org/W2563829177","https://openalex.org/W2580909119","https://openalex.org/W2583816737","https://openalex.org/W2589152698","https://openalex.org/W2591904660","https://openalex.org/W2606411279","https://openalex.org/W2607311634","https://openalex.org/W2728201397","https://openalex.org/W2739573821","https://openalex.org/W2775113028","https://openalex.org/W2785729136","https://openalex.org/W2796154788","https://openalex.org/W2807910285","https://openalex.org/W2891503716","https://openalex.org/W2902782170","https://openalex.org/W2909713847","https://openalex.org/W2940866906","https://openalex.org/W2941665215","https://openalex.org/W2946260552","https://openalex.org/W2950394900","https://openalex.org/W2951438752","https://openalex.org/W2963489214","https://openalex.org/W2964263543","https://openalex.org/W2972359635","https://openalex.org/W3099324303","https://openalex.org/W3105092064","https://openalex.org/W3139377883","https://openalex.org/W4249362117","https://openalex.org/W4298023569","https://openalex.org/W6743368274","https://openalex.org/W6817273188"],"related_works":["https://openalex.org/W2174293926","https://openalex.org/W1568262226","https://openalex.org/W2068306051","https://openalex.org/W2611274969","https://openalex.org/W1565233491","https://openalex.org/W2378735651","https://openalex.org/W22707859","https://openalex.org/W4385386026","https://openalex.org/W3014749947","https://openalex.org/W2565226525"],"abstract_inverted_index":{"Interactive":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"has":[4,15],"been":[5],"successfully":[6],"used":[7],"in":[8,11,22,42,62],"various":[9],"applications":[10],"different":[12],"fields,":[13],"which":[14],"also":[16],"motivated":[17],"HCI":[18,60],"researchers":[19,37,61,80],"to":[20,32,45,84],"contribute":[21],"this":[23,26],"area.":[24],"In":[25],"paper,":[27],"we":[28,72],"survey":[29],"interactive":[30,63,87],"RL":[31,43,88],"empower":[33],"human-computer":[34],"interaction":[35,48],"(HCI)":[36],"with":[38,81],"the":[39,56],"technical":[40],"background":[41],"needed":[44],"design":[46,75],"new":[47,52],"techniques":[49],"and":[50,67],"propose":[51,73],"applications.":[53,89],"We":[54],"elucidate":[55],"roles":[57],"played":[58],"by":[59],"RL,":[64],"identifying":[65],"ideas":[66],"promising":[68],"research":[69],"directions.":[70],"Furthermore,":[71],"generic":[74],"principles":[76],"that":[77],"will":[78],"provide":[79],"a":[82],"guide":[83],"effectively":[85],"implement":[86]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}