{"id":"https://openalex.org/W3134125422","doi":"https://doi.org/10.1109/tmm.2021.3063620","title":"Zwei: A Self-Play Reinforcement Learning Framework for Video Transmission Services","display_name":"Zwei: A Self-Play Reinforcement Learning Framework for Video Transmission Services","publication_year":2021,"publication_date":"2021-03-05","ids":{"openalex":"https://openalex.org/W3134125422","doi":"https://doi.org/10.1109/tmm.2021.3063620","mag":"3134125422"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3063620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3063620","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5057477098","display_name":"Tianchi Huang","orcid":"https://orcid.org/0000-0001-9378-6329"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianchi Huang","raw_affiliation_strings":["Beijing Key Laboratory of Networked Multimedia, Department of Computer Science and Technology, Tsinghua University, Beijing, China","BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Networked Multimedia, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085140543","display_name":"Rui-Xiao Zhang","orcid":"https://orcid.org/0000-0002-4251-825X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui-Xiao Zhang","raw_affiliation_strings":["Beijing Key Laboratory of Networked Multimedia, Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Networked Multimedia, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047712495","display_name":"Lifeng Sun","orcid":"https://orcid.org/0000-0002-4057-5138"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifeng Sun","raw_affiliation_strings":["BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China","Beijing Key Laboratory of Networked Multimedia, Department of Computer Science and Technology, Tsinghua University, Beijing, China","Key Laboratory of Pervasive Computing (Tsinghua University), Ministry of Education, China"],"affiliations":[{"raw_affiliation_string":"BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing Key Laboratory of Networked Multimedia, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Key Laboratory of Pervasive Computing (Tsinghua University), Ministry of Education, China","institution_ids":["https://openalex.org/I1327237609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057477098"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.9377,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.87886991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"24","issue":null,"first_page":"1350","last_page":"1365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9968000054359436,"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":0.9968000054359436,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9821000099182129,"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"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9684000015258789,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.8622002601623535},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6606208682060242},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5148152709007263},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.4302735924720764},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42326992750167847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.295049786567688},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16610196232795715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8622002601623535},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6606208682060242},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5148152709007263},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.4302735924720764},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42326992750167847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.295049786567688},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16610196232795715}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3063620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3063620","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6658023004","display_name":null,"funder_award_id":"61936011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G797295151","display_name":null,"funder_award_id":"61521002","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1556859836","https://openalex.org/W1587022413","https://openalex.org/W1597864774","https://openalex.org/W1976944900","https://openalex.org/W1997353980","https://openalex.org/W2001755333","https://openalex.org/W2055165550","https://openalex.org/W2151657298","https://openalex.org/W2152178735","https://openalex.org/W2158542147","https://openalex.org/W2175325787","https://openalex.org/W2257979135","https://openalex.org/W2397506972","https://openalex.org/W2482797934","https://openalex.org/W2547875792","https://openalex.org/W2736601468","https://openalex.org/W2737019897","https://openalex.org/W2744628735","https://openalex.org/W2751447593","https://openalex.org/W2759880155","https://openalex.org/W2769944055","https://openalex.org/W2802214001","https://openalex.org/W2810731248","https://openalex.org/W2849781392","https://openalex.org/W2906364736","https://openalex.org/W2913409451","https://openalex.org/W2950940817","https://openalex.org/W2950956365","https://openalex.org/W2954711779","https://openalex.org/W2963191323","https://openalex.org/W2965671543","https://openalex.org/W2966416749","https://openalex.org/W2978360652","https://openalex.org/W2996896271","https://openalex.org/W2998394761","https://openalex.org/W3010883527","https://openalex.org/W3013828496","https://openalex.org/W3029640231","https://openalex.org/W3047132563","https://openalex.org/W3047449906","https://openalex.org/W3048353667","https://openalex.org/W3048833701","https://openalex.org/W3058810697","https://openalex.org/W3087963932","https://openalex.org/W3099821090","https://openalex.org/W3100357905","https://openalex.org/W3101359755","https://openalex.org/W3160502863","https://openalex.org/W6637388848","https://openalex.org/W6692846177","https://openalex.org/W6698518210","https://openalex.org/W6729448088","https://openalex.org/W6736485827","https://openalex.org/W6741002519","https://openalex.org/W6758729514","https://openalex.org/W6765213128","https://openalex.org/W6775289199","https://openalex.org/W6781880021","https://openalex.org/W6781998056"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Video":[0],"transmission":[1,113],"services":[2],"adopt":[3],"adaptive":[4,116,178],"algorithms":[5],"to":[6,35,100,133,158],"ensure":[7],"users\u2019":[8],"demands.":[9],"Existing":[10],"techniques":[11],"are":[12],"often":[13,33],"optimized":[14],"and":[15,82,123,182],"evaluated":[16],"by":[17,64],"a":[18,55],"function":[19,32],"that":[20,29,60,128],"linearly":[21],"combines":[22],"several":[23],"weighted":[24],"metrics.":[25],"Nevertheless,":[26],"we":[27,147],"observe":[28],"the":[30,37,42,46,62,67,75,78,85,89,93,101,134,139,160,163,177,184,187],"given":[31],"fails":[34],"describe":[36],"requirement":[38,136],"accurately,":[39],"resulting":[40],"in":[41,162,176],"violation":[43],"of":[44,186],"generating":[45],"required":[47],"methods.":[48],"We":[49,104,169],"propose":[50,149],"<italic":[51,150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[52,151,173],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Zwei</i>":[53],",":[54,154],"self-play":[56],"reinforcement":[57,166],"learning":[58,167],"framework":[59],"updates":[61],"policy":[63],"straightforwardly":[65],"utilizing":[66],"actual":[68],"requirement.":[69,103],"Technically,":[70],"Zwei":[71,106,129,157,171],"effectively":[72],"rolls":[73],"out":[74],"trajectories":[76],"from":[77],"same":[79],"initial":[80],"state,":[81],"instantly":[83],"estimate":[84],"win":[86],"rate":[87],"w.r.t":[88],"competition":[90],"outcome,":[91],"where":[92],"outcome":[94],"represents":[95],"which":[96,155],"trajectory":[97],"is":[98],"closer":[99],"assigned":[102,135],"evaluate":[105],"with":[107],"different":[108],"requirements":[109],"on":[110],"various":[111],"video":[112],"tasks,":[114],"including":[115],"bitrate":[117,179],"streaming,":[118],"crowd-sourced":[119],"live":[120],"streaming":[121,180],"scheduling,":[122],"real-time":[124],"communication.":[125],"Results":[126],"indicate":[127],"optimizes":[130],"itself":[131],"according":[132],"faithfully,":[137],"outperforming":[138],"state-of-the-art":[140,192],"methods":[141],"under":[142],"all":[143],"considered":[144],"scenarios.":[145],"Moreover,":[146],"further":[148],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Zwei<inline-formula><tex-math":[152],"notation=\"LaTeX\">$^+$</tex-math></inline-formula></i>":[153],"enables":[156],"learn":[159],"policies":[161],"vanilla":[164],"no-regret":[165],"scenario.":[168],"validate":[170],"<inline-formula":[172],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[174],"notation=\"LaTeX\">$^+$</tex-math></inline-formula>":[175],"task":[181],"show":[183],"superiority":[185],"proposed":[188],"method":[189],"over":[190],"existing":[191],"approaches.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}