{"id":"https://openalex.org/W4296591833","doi":"https://doi.org/10.1145/3523227.3547370","title":"Hands-on Reinforcement Learning for Recommender Systems - From Bandits to SlateQ to Offline RL with Ray RLlib","display_name":"Hands-on Reinforcement Learning for Recommender Systems - From Bandits to SlateQ to Offline RL with Ray RLlib","publication_year":2022,"publication_date":"2022-09-13","ids":{"openalex":"https://openalex.org/W4296591833","doi":"https://doi.org/10.1145/3523227.3547370"},"language":"en","primary_location":{"id":"doi:10.1145/3523227.3547370","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523227.3547370","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/A5060220856","display_name":"Christy D. Bergman","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Christy D. Bergman","raw_affiliation_strings":["Anyscale, United States"],"affiliations":[{"raw_affiliation_string":"Anyscale, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078816526","display_name":"Kourosh Hakhamaneshi","orcid":"https://orcid.org/0000-0001-7922-2666"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kourosh Hakhamaneshi","raw_affiliation_strings":["Anyscale Inc., United States"],"affiliations":[{"raw_affiliation_string":"Anyscale Inc., United States","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060220856"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12647345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"700","last_page":"701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9997000098228455,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.991599977016449,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8639293909072876},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.8543668985366821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8411004543304443},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.711092472076416},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.5547670125961304},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5202456712722778},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5124826431274414},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.47250044345855713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4683339595794678},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.42513716220855713},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4139018654823303},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3746229112148285},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.33934447169303894},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.23085710406303406}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8639293909072876},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8543668985366821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8411004543304443},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.711092472076416},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.5547670125961304},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5202456712722778},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5124826431274414},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.47250044345855713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4683339595794678},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.42513716220855713},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4139018654823303},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3746229112148285},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.33934447169303894},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.23085710406303406},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3523227.3547370","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523227.3547370","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2892110489","https://openalex.org/W2902572901","https://openalex.org/W2918844309","https://openalex.org/W3087898974","https://openalex.org/W3200328667"],"related_works":["https://openalex.org/W2147117292","https://openalex.org/W2364921833","https://openalex.org/W2385146268","https://openalex.org/W1596010778","https://openalex.org/W4310607303","https://openalex.org/W4283818187","https://openalex.org/W3010663160","https://openalex.org/W2736068468","https://openalex.org/W1911735095","https://openalex.org/W2140060548"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,12],"(RL)":[2],"is":[3,77],"gaining":[4],"traction":[5],"as":[6],"a":[7,66,120,134],"complementary":[8],"approach":[9],"to":[10,16,19,44],"supervised":[11],"for":[13,24,54,73,90,131],"RecSys":[14,56,132],"due":[15],"its":[17],"ability":[18,43],"solve":[20],"sequential":[21],"decision-making":[22],"processes":[23],"delayed":[25],"rewards.":[26],"Recent":[27],"advances":[28],"in":[29,47],"offline":[30],"reinforcement":[31],"learning,":[32],"off-policy":[33],"evaluation,":[34],"and":[35,99],"more":[36,52],"scalable,":[37],"performant":[38],"system":[39],"design":[40],"with":[41,119],"the":[42,55],"run":[45,101],"code":[46,128],"parallel,":[48],"have":[49],"made":[50],"RL":[51,70,127],"tractable":[53],"real":[57],"time":[58],"use":[59],"cases.":[60],"This":[61],"tutorial":[62,118],"introduces":[63],"RLlib":[64,76,100,130],"[9],":[65],"comprehensive":[67],"open-source":[68,82],"Python":[69,91,126],"framework":[71,89],"built":[72,78],"production":[74],"workloads.":[75],"on":[79,102,105,133],"top":[80],"of":[81,124],"Ray":[83,98],"[8],":[84],"an":[85],"easy-to-use,":[86],"distributed":[87],"computing":[88],"that":[92],"can":[93],"handle":[94],"complex,":[95],"heterogeneous":[96],"applications.":[97],"compute":[103],"clusters":[104],"any":[106],"cloud":[107],"without":[108],"vendor":[109],"lock.":[110],"Using":[111],"Colab":[112],"notebooks,":[113],"you":[114],"will":[115],"leave":[116],"this":[117],"complete,":[121],"working":[122],"example":[123],"parallelized":[125],"using":[129],"github":[135],"repo.":[136]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}