{"id":"https://openalex.org/W7161140108","doi":"https://doi.org/10.1109/dcc66757.2026.00063","title":"A Search Method for Approximate Optimal Rate Control Solution via Reinforcement Learning","display_name":"A Search Method for Approximate Optimal Rate Control Solution via Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7161140108","doi":"https://doi.org/10.1109/dcc66757.2026.00063"},"language":null,"primary_location":{"id":"doi:10.1109/dcc66757.2026.00063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dcc66757.2026.00063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Data Compression Conference (DCC)","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/A5023974832","display_name":"Longtao Feng","orcid":null},"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":true,"raw_author_name":"Longtao Feng","raw_affiliation_strings":["School of Computer Science, Peking University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136112944","display_name":"Qian Yin","orcid":null},"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":"Qian Yin","raw_affiliation_strings":["School of Computer Science, Peking University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125185972","display_name":"H Xu","orcid":null},"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":"Xu Han","raw_affiliation_strings":["School of Computer Science, Peking University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136149688","display_name":"Jiaqi Zhang","orcid":null},"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":"Jiaqi Zhang","raw_affiliation_strings":["School of Computer Science, Peking University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100297578","display_name":"Yuwen He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuwen He","raw_affiliation_strings":["Bytedance Inc.,San Diego,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc.,San Diego,CA,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039832462","display_name":"Siwei Ma","orcid":"https://orcid.org/0000-0002-2731-5403"},"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":"Siwei Ma","raw_affiliation_strings":["School of Computer Science, Peking University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023974832"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94395611,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.6349999904632568,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.6349999904632568,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.09520000219345093,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.05000000074505806,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4763999879360199},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4327000081539154},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.39640000462532043},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.390500009059906},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.35120001435279846},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.3100999891757965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5123999714851379},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43290001153945923},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.390500009059906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38019999861717224},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C155386361","wikidata":"https://www.wikidata.org/wiki/Q1649571","display_name":"Process control","level":3,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dcc66757.2026.00063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dcc66757.2026.00063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Data Compression Conference (DCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2206677354","display_name":null,"funder_award_id":"62025101,62088102,62501022","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"studies":[1],"on":[2,96,174],"video":[3,75],"rate":[4],"control":[5],"(RC)":[6],"have":[7,15],"introduced":[8],"accurate":[9],"and":[10,31,105,119,123,157,214,235,238],"high":[11],"performance":[12],"methods":[13,30],"but":[14],"not":[16],"explored":[17],"the":[18,49,70,87,97,126,130,140,150,154,162,166,175,184,202,211,218,225,248],"optimal":[19,23,40,62,168,226],"RC":[20,29,41,63,71,135,145,169,176],"solution.":[21],"The":[22],"solution":[24,146,170],"is":[25,76,112,147,171,190],"crucial":[26],"for":[27,34,59,73],"improving":[28],"providing":[32],"labels":[33],"supervised":[35],"learning.":[36],"To":[37],"find":[38],"approximate":[39,61,167],"solutions":[42,64,136,177,219],"within":[43,65,125],"a":[44,53,66,74,80,92,120,158,242],"limited":[45,67],"time,":[46],"we":[47,90],"are":[48,137,239],"first":[50,77],"to":[51,128,247],"propose":[52],"reinforcement":[54],"learning":[55],"based":[56,95,173],"search":[57,93],"method":[58,94,189,223],"finding":[60],"time.":[68],"Specifically,":[69],"problem":[72],"modeled":[78],"as":[79],"Markov":[81],"decision":[82],"process":[83],"(MDP).":[84],"Then,":[85],"with":[86,228],"MDP":[88,127],"model,":[89],"develop":[91],"deep":[98],"Q-network":[99],"method,":[100],"which":[101],"consists":[102],"of":[103,115,187,204,217,230],"exploration":[104],"exploitation":[106,163],"steps.":[107,181],"During":[108],"exploration,":[109],"an":[110],"agent":[111,152],"created,":[113],"consisting":[114],"two":[116,180],"multilayer":[117],"perceptrons":[118],"replay":[121],"memory,":[122],"trained":[124,151],"estimate":[129],"value":[131,155],"function,":[132],"while":[133],"superior":[134],"recorded":[138],"throughout":[139],"training":[141,205],"process.":[142],"After":[143],"training,":[144],"estimated":[148],"by":[149,221],"using":[153],"function":[156],"greedy":[159],"strategy":[160],"during":[161],"step.":[164],"Finally,":[165],"determined":[172],"from":[178],"both":[179],"In":[182],"addition,":[183],"time":[185,245],"complexity":[186],"proposed":[188,222],"controllable,":[191],"specifically,":[192],"<tex":[193,198],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[194,199],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$O(m":[195],"n)$</tex>":[196],"where":[197],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$m$</tex>":[200],"denotes":[201],"number":[203],"epoch.":[206],"Experimental":[207],"results":[208],"show":[209],"that":[210],"bit-rate":[212],"error":[213],"compression":[215],"quality":[216],"found":[220],"approach":[224],"solutions,":[227],"differences":[229],"only":[231],"less":[232],"than":[233],"0.005%":[234],"0.399%,":[236],"respectively,":[237],"achieved":[240],"in":[241],"significantly":[243],"shorter":[244],"compared":[246],"brute":[249],"force":[250],"search.":[251]},"counts_by_year":[],"updated_date":"2026-05-16T06:04:12.930555","created_date":"2026-05-15T00:00:00"}