{"id":"https://openalex.org/W4377981550","doi":"https://doi.org/10.1145/3592473.3592564","title":"Improving ABR Performance for Short Video Streaming Using Multi-Agent Reinforcement Learning with Expert Guidance","display_name":"Improving ABR Performance for Short Video Streaming Using Multi-Agent Reinforcement Learning with Expert Guidance","publication_year":2023,"publication_date":"2023-05-24","ids":{"openalex":"https://openalex.org/W4377981550","doi":"https://doi.org/10.1145/3592473.3592564"},"language":"en","primary_location":{"id":"doi:10.1145/3592473.3592564","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592473.3592564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd Workshop on Network and Operating System Support for Digital Audio and Video","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/A5051972415","display_name":"Yueheng Li","orcid":"https://orcid.org/0000-0002-2740-1993"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yueheng Li","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084650785","display_name":"Qianyuan Zheng","orcid":"https://orcid.org/0009-0009-4987-2604"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianyuan Zheng","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101797196","display_name":"Zicheng Zhang","orcid":"https://orcid.org/0009-0000-4474-7702"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zicheng Zhang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079335291","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0002-1179-8199"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073914656","display_name":"Zhan Ma","orcid":"https://orcid.org/0000-0003-3686-4057"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Ma","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051972415"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":2.1354,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89325278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"58","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11165","display_name":"Image and Video Quality Assessment","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8572719693183899},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7659506797790527},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.5189954042434692},{"id":"https://openalex.org/keywords/quality-of-experience","display_name":"Quality of experience","score":0.48656144738197327},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4722135663032532},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.4646584093570709},{"id":"https://openalex.org/keywords/variable-bitrate","display_name":"Variable bitrate","score":0.43824654817581177},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4361236095428467},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.3071874976158142},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2972453832626343},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2882782518863678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8572719693183899},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7659506797790527},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.5189954042434692},{"id":"https://openalex.org/C2779333187","wikidata":"https://www.wikidata.org/wiki/Q3132648","display_name":"Quality of experience","level":3,"score":0.48656144738197327},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4722135663032532},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4646584093570709},{"id":"https://openalex.org/C57667952","wikidata":"https://www.wikidata.org/wiki/Q1154443","display_name":"Variable bitrate","level":3,"score":0.43824654817581177},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4361236095428467},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.3071874976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2972453832626343},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2882782518863678},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3592473.3592564","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592473.3592564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd Workshop on Network and Operating System Support for Digital Audio and Video","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6716339259","display_name":null,"funder_award_id":"62101241","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":18,"referenced_works":["https://openalex.org/W616265588","https://openalex.org/W2396217537","https://openalex.org/W2492794003","https://openalex.org/W2604382266","https://openalex.org/W2736601468","https://openalex.org/W2744628735","https://openalex.org/W2849781392","https://openalex.org/W2965671543","https://openalex.org/W2997214666","https://openalex.org/W3030583461","https://openalex.org/W3101359755","https://openalex.org/W3210224682","https://openalex.org/W4211024378","https://openalex.org/W4283320228","https://openalex.org/W4286748781","https://openalex.org/W4297816725","https://openalex.org/W4304087114","https://openalex.org/W4304091883"],"related_works":["https://openalex.org/W2280226702","https://openalex.org/W2044415708","https://openalex.org/W2883239366","https://openalex.org/W2663282472","https://openalex.org/W1543922763","https://openalex.org/W3127182254","https://openalex.org/W1971541619","https://openalex.org/W2737069248","https://openalex.org/W2914450980","https://openalex.org/W2542002904"],"abstract_inverted_index":{"In":[0],"the":[1,53,100,118,142,150,162,173],"realm":[2],"of":[3,56,102,127,152],"short":[4,31],"video":[5,16,32,42,103,106],"streaming,":[6],"popular":[7],"adaptive":[8,33],"bitrate":[9,34,45,107,113],"(ABR)":[10],"algorithms":[11,36],"developed":[12],"for":[13,48],"classical":[14],"long":[15],"applications":[17],"suffer":[18],"from":[19,155],"catastrophic":[20],"failures":[21],"because":[22],"they":[23],"are":[24,69],"tuned":[25],"to":[26,38,98,116],"solely":[27],"adapt":[28],"bitrates.":[29],"Instead,":[30],"(SABR)":[35],"have":[37],"properly":[39],"determine":[40],"which":[41,44],"at":[43],"level":[46],"together":[47],"content":[49],"prefetching,":[50],"without":[51],"sacrificing":[52],"users'":[54],"quality":[55],"experience":[57],"(QoE)":[58],"and":[59,75,105,112,129,146,181],"yielding":[60],"noticeable":[61],"bandwidth":[62,130],"wastage":[63,131],"jointly.":[64],"Unfortunately,":[65],"existing":[66],"SABR":[67,87,165],"methods":[68],"inevitably":[70],"entangled":[71],"with":[72,95,167],"slow":[73],"convergence":[74],"poor":[76],"generalization.":[77],"Thus,":[78],"in":[79,108],"this":[80],"paper,":[81],"we":[82],"propose":[83],"Incendio,":[84,135],"a":[85,124,168],"novel":[86],"framework":[88],"that":[89,159],"applies":[90],"Multi-Agent":[91],"Reinforcement":[92],"Learning":[93],"(MARL)":[94],"Expert":[96],"Guidance":[97],"separate":[99],"decision":[101],"ID":[104],"respective":[109],"buffer":[110],"management":[111],"adaptation":[114],"agents":[115],"maximize":[117],"system-level":[119],"utilized":[120],"score":[121,175],"modeled":[122],"as":[123],"compound":[125],"function":[126],"QoE":[128],"metrics.":[132],"To":[133],"train":[134],"it":[136],"is":[137],"first":[138],"initialized":[139],"by":[140,172],"imitating":[141],"hand-crafted":[143],"expert":[144],"rules":[145],"then":[147],"fine-tuned":[148],"through":[149],"use":[151],"MARL.":[153],"Results":[154],"extensive":[156],"experiments":[157],"indicate":[158],"Incendio":[160],"outperforms":[161],"current":[163],"state-of-the-art":[164],"algorithm":[166],"53.2%":[169],"improvement":[170],"measured":[171],"utility":[174],"while":[176],"maintaining":[177],"low":[178],"training":[179],"complexity":[180],"inference":[182],"time.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}