{"id":"https://openalex.org/W4296591823","doi":"https://doi.org/10.1145/3523227.3547376","title":"Conversational Recommender System Using Deep Reinforcement Learning","display_name":"Conversational Recommender System Using Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-09-13","ids":{"openalex":"https://openalex.org/W4296591823","doi":"https://doi.org/10.1145/3523227.3547376"},"language":"en","primary_location":{"id":"doi:10.1145/3523227.3547376","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523227.3547376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Conference on Recommender Systems","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/A5070053484","display_name":"Omprakash Sonie","orcid":"https://orcid.org/0000-0003-4726-6765"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Omprakash Sonie","raw_affiliation_strings":["Data Science, DeepThinking.AI, India"],"affiliations":[{"raw_affiliation_string":"Data Science, DeepThinking.AI, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070053484"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9094,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79839864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"718","last_page":"719"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9818000197410583,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9818000197410583,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9598000049591064,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.914900004863739,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9493895173072815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7381269335746765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6983696222305298},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6858236789703369},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.6143792867660522},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5584525465965271},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.524316668510437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34376630187034607},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11158126592636108},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.07410401105880737}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9493895173072815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7381269335746765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6983696222305298},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6858236789703369},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.6143792867660522},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5584525465965271},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.524316668510437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34376630187034607},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11158126592636108},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.07410401105880737},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3523227.3547376","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523227.3547376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Conference on Recommender Systems","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":9,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2788295351","https://openalex.org/W2963619374","https://openalex.org/W3038439974","https://openalex.org/W3091977701","https://openalex.org/W3100790518","https://openalex.org/W3102778384","https://openalex.org/W3199574933","https://openalex.org/W4290878490"],"related_works":["https://openalex.org/W2557924869","https://openalex.org/W4380075502","https://openalex.org/W2888481972","https://openalex.org/W2907945115","https://openalex.org/W4223943233","https://openalex.org/W4312200629","https://openalex.org/W4360585206","https://openalex.org/W4364306694","https://openalex.org/W4380086463","https://openalex.org/W4225161397"],"abstract_inverted_index":{"Deep":[0,12,24,66,71,112],"Reinforcement":[1,9,25,63,67,109,113],"Learning":[2,10,13,26,64,68,110],"(DRL)":[3],"uses":[4],"the":[5,52,120],"best":[6],"of":[7,54],"both":[8],"and":[11,65,69,75,100,111],"for":[14,31,40,43,56,108],"solving":[15],"problems":[16],"which":[17],"cannot":[18],"be":[19],"addressed":[20],"by":[21],"them":[22],"individually.":[23],"has":[27,37],"been":[28,38],"used":[29],"widely":[30],"games,":[32],"robotics":[33],"etc.":[34],"Limited":[35],"work":[36],"done":[39],"applying":[41],"DRL":[42,55],"Conversational":[44],"Recommender":[45],"System":[46],"(CRS).":[47],"Hence,":[48],"this":[49],"tutorial":[50],"covers":[51],"application":[53],"CRS.":[57],"We":[58,79,103],"give":[59],"conceptual":[60],"introduction":[61],"to":[62,105],"cover":[70,81],"Q-Network,":[72],"Dyna,":[73],"REINFORCE":[74],"Actor":[76],"Critic":[77],"methods.":[78],"then":[80],"various":[82],"real":[83],"life":[84],"case":[85],"studies":[86],"with":[87],"increasing":[88],"complexity":[89],"starting":[90],"from":[91],"CRS,":[92,94,98],"deep":[93,99],"adaptivity,":[95],"topic":[96],"guided":[97],"large-scale":[101],"CRSs.":[102],"plan":[104],"share":[106],"pre-read":[107],"learning":[114],"so":[115],"that":[116],"participants":[117],"can":[118],"grasp":[119],"material":[121],"well.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}