{"id":"https://openalex.org/W3209358509","doi":"https://doi.org/10.1145/3486001.3486244","title":"Towards Accelerating Offline RL based Recommender Systems","display_name":"Towards Accelerating Offline RL based Recommender Systems","publication_year":2021,"publication_date":"2021-10-21","ids":{"openalex":"https://openalex.org/W3209358509","doi":"https://doi.org/10.1145/3486001.3486244","mag":"3209358509"},"language":"en","primary_location":{"id":"doi:10.1145/3486001.3486244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3486001.3486244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The First International Conference on AI-ML-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/A5101566702","display_name":"Mayank Mishra","orcid":"https://orcid.org/0000-0002-4654-1246"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Mayank Mishra","raw_affiliation_strings":["TCS Research, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086400313","display_name":"Rekha Singhal","orcid":"https://orcid.org/0000-0002-3712-1784"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rekha Singhal","raw_affiliation_strings":["TCS Research, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012558920","display_name":"Ravi Kumar Singh","orcid":"https://orcid.org/0009-0009-9547-5968"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ravi Singh","raw_affiliation_strings":["TCS Research, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101566702"],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":0.2754,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63910059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.996399998664856,"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":0.996399998664856,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.994700014591217,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9873999953269958,"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/recommender-system","display_name":"Recommender system","score":0.8108274340629578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7830886840820312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3474748432636261},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2609770894050598}],"concepts":[{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8108274340629578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830886840820312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3474748432636261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2609770894050598}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3486001.3486244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3486001.3486244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The First International Conference on AI-ML-Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2734941459","https://openalex.org/W2739473244","https://openalex.org/W2807799957","https://openalex.org/W2899457523","https://openalex.org/W2914209329","https://openalex.org/W2979211489","https://openalex.org/W3022566517","https://openalex.org/W3043057128","https://openalex.org/W3101707147","https://openalex.org/W3113207880","https://openalex.org/W3123348991","https://openalex.org/W3137046406"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W3197542405","https://openalex.org/W2056712470","https://openalex.org/W3125580266","https://openalex.org/W4317039510"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,7,43],"optimizes":[2],"an":[3,8,18,33,37,40],"objective":[4],"function":[5],"by":[6,174,185],"optimal":[9],"policy":[10,27,119,149],"for":[11,117,126],"taking":[12],"a":[13,23,74,107,175,181],"sequence":[14],"of":[15,32,47,109,140,151,167,177],"actions":[16],"in":[17,36,83,95],"environment.":[19],"Offline":[20],"RL":[21,57,76,115,169],"is":[22],"mechanism":[24],"to":[25,59,68],"learn":[26,69],"offline":[28,56,99],"from":[29],"pre-generated":[30],"traces":[31],"agent\u2019s":[34,41],"interactions":[35],"environment,":[38],"accelerating":[39,96],"initial":[42],"phase.":[44],"Real-time":[45],"deployment":[46],"RL-based":[48,100],"recommenders":[49],"across":[50],"geographies":[51],"could":[52,162],"mix":[53,108],"online":[54],"and":[55,64,81,93,113,137,142,148],"algorithms":[58,116],"explore":[60],"new":[61],"users\u2019":[62],"behavior":[63],"exploit":[65],"old":[66],"knowledge":[67],"recommendation":[70],"policy.":[71],"In":[72,86],"such":[73,129],"scenario,":[75],"agents":[77,170],"will":[78],"be":[79],"distributed":[80,144],"deployed":[82],"multiple":[84],"locations.":[85],"this":[87,127],"paper,":[88],"we":[89],"share":[90],"our":[91,97],"experiences":[92],"learnings":[94],"in-house":[98],"recommender":[101,104],"system.":[102],"The":[103],"system":[105],"employs":[106],"Batch":[110],"Constrained":[111],"(BCQ)":[112],"distributional":[114],"building":[118],"models.":[120],"We":[121,154],"present":[122],"various":[123],"acceleration":[124,160],"techniques":[125,161],"system,":[128],"as":[130],"operators\u2019":[131],"fusion,":[132],"performance":[133],"anti-patterns,":[134],"heterogeneous":[135],"deployments,":[136],"design":[138],"space":[139],"synchronous":[141],"asynchronous":[143],"training":[145,166],"over":[146,180],"generative":[147],"models":[150],"the":[152,158,165,168,186],"algorithm.":[153],"have":[155],"shown":[156],"that":[157],"presented":[159],"speed":[163],"up":[164],"on":[171,190],"A100":[172],"GPUs":[173],"factor":[176],"47":[178],"\u00d7":[179],"naive":[182],"code":[183],"(written":[184],"ML":[187],"practitioner)":[188],"implementation":[189],"A100.":[191]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}