{"id":"https://openalex.org/W3205139033","doi":"https://doi.org/10.1145/3474085.3478323","title":"Efficient Reinforcement Learning Development with RLzoo","display_name":"Efficient Reinforcement Learning Development with RLzoo","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205139033","doi":"https://doi.org/10.1145/3474085.3478323","mag":"3205139033"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3478323","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3478323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5002742139","display_name":"Zihan Ding","orcid":"https://orcid.org/0009-0005-2008-4816"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zihan Ding","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064045506","display_name":"Tianyang Yu","orcid":"https://orcid.org/0000-0002-7534-6175"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyang Yu","raw_affiliation_strings":["Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445026","display_name":"Hongming Zhang","orcid":"https://orcid.org/0000-0001-6133-693X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongming Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028455806","display_name":"Yanhua H. Huang","orcid":"https://orcid.org/0000-0003-1770-0196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanhua Huang","raw_affiliation_strings":["Xiaohongshu Technology Co., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Xiaohongshu Technology Co., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101490891","display_name":"Li Guo","orcid":"https://orcid.org/0000-0002-2707-5833"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guo Li","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068860009","display_name":"Quancheng Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Quancheng Guo","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101924633","display_name":"Luo Mai","orcid":"https://orcid.org/0000-0002-7712-7558"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luo Mai","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100709867","display_name":"Hao Dong","orcid":"https://orcid.org/0000-0002-7984-9909"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Dong","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5002742139"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63813351,"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":"3759","last_page":"3762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9932000041007996,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9549999833106995,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7286561131477356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6532135605812073},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43447208404541016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36246728897094727},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15491333603858948}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7286561131477356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6532135605812073},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43447208404541016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36246728897094727},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15491333603858948},{"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:10.1145/3474085.3478323","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3478323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4612480795","display_name":null,"funder_award_id":"62006006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2402144811","https://openalex.org/W2738092912","https://openalex.org/W2786036274","https://openalex.org/W2949608212","https://openalex.org/W2963094322","https://openalex.org/W2963390429","https://openalex.org/W2963967766","https://openalex.org/W2964374138","https://openalex.org/W2998544442","https://openalex.org/W2999862950","https://openalex.org/W3007769740","https://openalex.org/W3206040568","https://openalex.org/W4211007122","https://openalex.org/W4299967799"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2076061571","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847"],"abstract_inverted_index":{"Many":[0],"multimedia":[1],"developers":[2,49,80],"are":[3,132],"exploring":[4],"for":[5,29,87,96],"adopting":[6],"Deep":[7],"Reinforcement":[8],"Learning":[9],"(DRL)":[10],"techniques":[11],"in":[12,54,138],"their":[13,116],"applications.":[14],"They":[15],"however":[16],"often":[17,50],"find":[18],"such":[19],"an":[20,120],"adoption":[21],"challenging.":[22],"Existing":[23],"DRL":[24,31,43,56,66,75,89,111,126,153,161],"libraries":[25],"provide":[26],"poor":[27],"support":[28],"prototyping":[30,88],"agents":[32,76,95,112,127],"(i.e.,":[33],"models),":[34],"customising":[35,93],"the":[36,40,48,72,94,149],"agents,":[37,90,154],"and":[38,91,113,118],"comparing":[39],"performance":[41,137,158],"of":[42,74,110,152],"agents.":[44,57],"As":[45],"a":[46,64,100,107],"result,":[47],"report":[51],"low":[52],"efficiency":[53],"developing":[55],"In":[58],"this":[59],"paper,":[60],"we":[61],"introduce":[62],"RLzoo,":[63],"new":[65],"library":[67],"that":[68,122,144],"aims":[69],"to":[70,134],"make":[71],"development":[73,150],"efficient.":[77],"RLzoo":[78,145],"provides":[79],"with":[81,128,159],"(i)":[82],"high-level":[83],"yet":[84],"flexible":[85],"APIs":[86],"further":[92],"best":[97],"performance,":[98,117],"(ii)":[99],"model":[101],"zoo":[102],"where":[103],"users":[104],"can":[105,123,146],"import":[106],"wide":[108],"range":[109],"easily":[114],"compare":[115],"(iii)":[119],"algorithm":[121],"automatically":[124],"construct":[125],"custom":[129,139],"components":[130],"(which":[131],"critical":[133],"improve":[135],"agent's":[136],"applications).":[140],"Evaluation":[141],"results":[142],"show":[143],"effectively":[147],"reduce":[148],"cost":[151],"while":[155],"achieving":[156],"comparable":[157],"existing":[160],"libraries.":[162]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}