{"id":"https://openalex.org/W3128719019","doi":"https://doi.org/10.1145/3437378.3437395","title":"Establishing a Dialog Agent Policy using Deep Reinforcement Learning in the Psychotherapy Domain","display_name":"Establishing a Dialog Agent Policy using Deep Reinforcement Learning in the Psychotherapy Domain","publication_year":2021,"publication_date":"2021-02-01","ids":{"openalex":"https://openalex.org/W3128719019","doi":"https://doi.org/10.1145/3437378.3437395","mag":"3128719019"},"language":"en","primary_location":{"id":"doi:10.1145/3437378.3437395","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437378.3437395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Australasian Computer Science Week Multiconference","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/A5019165192","display_name":"Chester Holt\u2010Quick","orcid":"https://orcid.org/0000-0002-8350-919X"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Chester Holt-Quick","raw_affiliation_strings":["The University of Auckland, New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040739282","display_name":"Jim Warren","orcid":"https://orcid.org/0000-0002-8660-8951"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Jim Warren","raw_affiliation_strings":["The University of Auckland, New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019165192"],"corresponding_institution_ids":["https://openalex.org/I154130895"],"apc_list":null,"apc_paid":null,"fwci":0.4116,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60858288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"27","issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11519","display_name":"Digital Mental Health Interventions","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11519","display_name":"Digital Mental Health Interventions","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied 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/T12128","display_name":"AI in Service Interactions","score":0.9872000217437744,"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/T12031","display_name":"Speech and dialogue systems","score":0.9552000164985657,"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/dialog-box","display_name":"Dialog box","score":0.9732334613800049},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.736255407333374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6969371438026428},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6274843215942383},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.6089120507240295},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5294294953346252},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4893485903739929},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4118635356426239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33345934748649597},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2549402117729187},{"id":"https://openalex.org/keywords/psychotherapist","display_name":"Psychotherapist","score":0.2357408106327057},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1684509813785553},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08573174476623535}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9732334613800049},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.736255407333374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6969371438026428},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6274843215942383},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.6089120507240295},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5294294953346252},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4893485903739929},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4118635356426239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33345934748649597},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2549402117729187},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.2357408106327057},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1684509813785553},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08573174476623535},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3437378.3437395","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437378.3437395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Australasian Computer Science Week Multiconference","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":17,"referenced_works":["https://openalex.org/W434200312","https://openalex.org/W1516184288","https://openalex.org/W1958706068","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2289545039","https://openalex.org/W2612630960","https://openalex.org/W2623779865","https://openalex.org/W2783475269","https://openalex.org/W2804233548","https://openalex.org/W2895995041","https://openalex.org/W2949868354","https://openalex.org/W2963167310","https://openalex.org/W4236521339","https://openalex.org/W4254771578","https://openalex.org/W6600426076","https://openalex.org/W6679436768"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2394821827","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W1600043506","https://openalex.org/W2174703168","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2920931047"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"seen":[3],"a":[4,95,110,138,167],"rise":[5],"in":[6,54,76,131],"the":[7,61,77,92,145,155,175],"development":[8],"and":[9,20,51],"use":[10,93,165],"of":[11,27,44,63,94,141,144,166],"dialog":[12,42,74,111,170],"agents":[13],"(chatbots)":[14],"including":[15,91],"as":[16],"personal":[17],"friends,":[18],"coaches":[19],"even":[21],"counsellors":[22],"(Virtual":[23],"Counsellor,":[24],"VC).":[25],"Some":[26],"these":[28,45],"[1]":[29],"employ":[30],"expert":[31],"psychotherapy":[32,78],"techniques,":[33],"notably":[34],"Cognitive":[35],"Behavioural":[36],"Therapy":[37],"(CBT).":[38],"The":[39],"usually":[40],"rule-based":[41,162],"policy":[43,75,112],"chatbots":[46],"requires":[47],"significant":[48],"authoring":[49,132],"effort":[50,133],"can":[52,117,125,149],"result":[53],"overly":[55],"predictable":[56],"dialog.":[57],"This":[58],"research":[59],"examines":[60],"question":[62],"whether":[64],"using":[65],"deep":[66],"reinforcement":[67],"learning":[68],"(DRL)":[69],"to":[70,114],"develop":[71],"an":[72],"agent":[73],"domain":[79],"is":[80,89,99,107,134,158,172],"feasible.":[81],"A":[82,128],"framework":[83],"for":[84,86],"DRL":[85],"this":[87],"problem":[88],"established":[90],"user":[96,156],"simulator":[97,157],"that":[98,109,121],"configured":[100,159],"through":[101],"CBT":[102,123,147],"manual":[103],"transcript":[104,115],"excerpts.":[105],"It":[106],"found":[108],"conforming":[113],"excerpts":[116],"be":[118,126,150],"learned":[119,146],"such":[120],"core":[122],"skills":[124],"emulated.":[127],"hoped-for":[129],"reduction":[130],"not":[135],"seen,":[136],"but":[137],"modest":[139],"amount":[140],"local":[142],"generalisation":[143],"skill":[148],"observed":[151,173],"which":[152],"increases":[153],"when":[154],"with":[160],"additional":[161],"policies.":[163],"Interesting":[164],"novel":[168],"listening":[169],"move":[171],"by":[174],"trained":[176],"VC.":[177]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
