{"id":"https://openalex.org/W3204554024","doi":null,"title":"Deep Reinforcement Learning for Interactive Systems","display_name":"Deep Reinforcement Learning for Interactive Systems","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3204554024","mag":"3204554024"},"language":"en","primary_location":{"id":"pmh:oai:repository.library.georgetown.edu:10822/1062649","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10822/1062649","pdf_url":null,"source":{"id":"https://openalex.org/S4306402467","display_name":"DigitalGeorgetown (Georgetown University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210145449","host_organization_name":"Center for Security and Emerging Technology","host_organization_lineage":["https://openalex.org/I4210145449"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science","raw_type":"thesis"},"volume":null,"type":"dissertation","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/A5042237237","display_name":"Zhiwen Tang","orcid":"https://orcid.org/0000-0002-7404-4474","observed_orcids":["https://orcid.org/0000-0002-7404-4474"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhiwen Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5042237237"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9634000062942505,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9634000062942505,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.021800000220537186,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.009800000116229057,"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/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8889999985694885},{"id":"https://openalex.org/keywords/interactive-systems","display_name":"interactive systems","score":0.8899999856948853},{"id":"https://openalex.org/keywords/human-computer-interaction","display_name":"human-computer interaction","score":0.6290000081062317},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.5550000071525574}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6084636449813843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4784533977508545},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42223870754241943},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38185012340545654},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.33203327655792236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2893052399158478},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2697148323059082},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09732687473297119}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:repository.library.georgetown.edu:10822/1062649","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10822/1062649","pdf_url":null,"source":{"id":"https://openalex.org/S4306402467","display_name":"DigitalGeorgetown (Georgetown University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210145449","host_organization_name":"Center for Security and Emerging Technology","host_organization_lineage":["https://openalex.org/I4210145449"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science","raw_type":"thesis"},{"id":"mag:3204554024","doi":null,"is_oa":false,"landing_page_url":"https://repository.library.georgetown.edu/handle/10822/1062649","pdf_url":null,"source":{"id":"https://openalex.org/S2764685317","display_name":"Georgetown University-Graduate School of Arts & Sciences","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4323970070","host_organization_name":"Georgetown University","host_organization_lineage":["https://openalex.org/P4323970070"],"host_organization_lineage_names":["Georgetown University"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Georgetown University-Graduate School of Arts & Sciences","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":53,"referenced_works":["https://openalex.org/W299870200","https://openalex.org/W1539175566","https://openalex.org/W1557074680","https://openalex.org/W1591706642","https://openalex.org/W1597379241","https://openalex.org/W1840435438","https://openalex.org/W1991788574","https://openalex.org/W1998084297","https://openalex.org/W2021021687","https://openalex.org/W2042816580","https://openalex.org/W2042980227","https://openalex.org/W2067736059","https://openalex.org/W2100873065","https://openalex.org/W2121863487","https://openalex.org/W2130395434","https://openalex.org/W2136189984","https://openalex.org/W2136542423","https://openalex.org/W2143331230","https://openalex.org/W2153579005","https://openalex.org/W2156841666","https://openalex.org/W2158231614","https://openalex.org/W2536015822","https://openalex.org/W2539671052","https://openalex.org/W2592808142","https://openalex.org/W2605102758","https://openalex.org/W2624924938","https://openalex.org/W2745673470","https://openalex.org/W2752382061","https://openalex.org/W2767050701","https://openalex.org/W2793710388","https://openalex.org/W2798494119","https://openalex.org/W2810840719","https://openalex.org/W2888296173","https://openalex.org/W2890276793","https://openalex.org/W2945127593","https://openalex.org/W2950813464","https://openalex.org/W2951718443","https://openalex.org/W2951805158","https://openalex.org/W2963068985","https://openalex.org/W2964108915","https://openalex.org/W2964159778","https://openalex.org/W2970028737","https://openalex.org/W2982130342","https://openalex.org/W3012594078","https://openalex.org/W3021016503","https://openalex.org/W3030163527","https://openalex.org/W3033850452","https://openalex.org/W3034599929","https://openalex.org/W3045033475","https://openalex.org/W3104220682","https://openalex.org/W3105949871","https://openalex.org/W3106031848","https://openalex.org/W3156413894"],"related_works":["https://openalex.org/W2901707619","https://openalex.org/W4240612966","https://openalex.org/W7122481168","https://openalex.org/W7139173119","https://openalex.org/W7053166617","https://openalex.org/W7046007634","https://openalex.org/W7220706390","https://openalex.org/W4303182378","https://openalex.org/W7064826350","https://openalex.org/W7037017637"],"abstract_inverted_index":{"Artificial":[0],"intelligence":[1],"(AI)":[2],"aims":[3],"to":[4,29,32,50,90,107,137],"build":[5,91],"intelligent":[6],"systems":[7,82,144],"that":[8,93],"can":[9],"interact":[10],"with":[11],"and":[12,27,67,148],"assist":[13],"humans.":[14],"During":[15],"the":[16,21,24,30,44,64,68,99,105,109,122,149,157],"interaction,":[17],"a":[18,47,55,59,75],"system":[19,40,45,106],"learns":[20],"requirements":[22],"from":[23,54],"human":[25],"user":[26],"adapts":[28],"needs":[31],"complete":[33],"tasks.":[34],"A":[35],"popular":[36],"type":[37],"of":[38,63,98,117,124],"interactive":[39,65,81,118,143],"is":[41,83],"retrieval-based,":[42],"where":[43],"uses":[46],"retrieval":[48,110],"function":[49],"retrieve":[51],"relevant":[52],"answers":[53],"document":[56],"collection":[57],"or":[58,101],"knowledge":[60],"repository.":[61],"Because":[62],"setting":[66],"goal-oriented":[69],"objective,":[70],"reinforcement":[71],"learning":[72],"(RL)":[73],"becomes":[74],"trending":[76],"solution.":[77],"\\nHowever,":[78],"developing":[79],"RL-based":[80,125],"not":[84,103],"always":[85],"successful.":[86],"Prior":[87],"methods":[88],"failed":[89],"representations":[92],"provide":[94],"an":[95],"entire":[96],"picture":[97],"task":[100],"could":[102],"enable":[104],"control":[108],"results":[111],"directly.":[112],"The":[113,127,139],"costly":[114],"labeling":[115],"process":[116],"data":[119,134],"further":[120],"handicaps":[121],"application":[123],"methods.":[126],"RL":[128],"agents":[129],"trained":[130],"on":[131],"limited":[132],"annotated":[133],"may":[135,155],"fail":[136],"generalize.":[138],"evaluation":[140],"metrics":[141],"for":[142],"are":[145],"often":[146],"unbounded,":[147],"huge":[150],"variance":[151],"among":[152],"search":[153],"tasks":[154],"bias":[156],"evaluation.":[158]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2021-10-11T00:00:00"}