{"id":"https://openalex.org/W4402263848","doi":"https://doi.org/10.23919/acc60939.2024.10645022","title":"Near-Optimality of Finite-Memory Codes and Reinforcement Learning for Zero-Delay Coding of Markov Sources","display_name":"Near-Optimality of Finite-Memory Codes and Reinforcement Learning for Zero-Delay Coding of Markov Sources","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4402263848","doi":"https://doi.org/10.23919/acc60939.2024.10645022"},"language":"en","primary_location":{"id":"doi:10.23919/acc60939.2024.10645022","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc60939.2024.10645022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","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/A5093047920","display_name":"Liam Cregg","orcid":null},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Liam Cregg","raw_affiliation_strings":["Queen's University,Department of Mathematics and Statistics,Kingston,ON,Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University,Department of Mathematics and Statistics,Kingston,ON,Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065742137","display_name":"Fady Alajaji","orcid":"https://orcid.org/0000-0002-7980-724X"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fady Alajaji","raw_affiliation_strings":["Queen's University,Department of Mathematics and Statistics,Kingston,ON,Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University,Department of Mathematics and Statistics,Kingston,ON,Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005401257","display_name":"Serdar Y\u00fcksel","orcid":"https://orcid.org/0000-0001-6099-5001"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Serdar Y\u00fcksel","raw_affiliation_strings":["Queen's University,Department of Mathematics and Statistics,Kingston,ON,Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University,Department of Mathematics and Statistics,Kingston,ON,Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093047920"],"corresponding_institution_ids":["https://openalex.org/I204722609"],"apc_list":null,"apc_paid":null,"fwci":0.3755,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61273747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4170","last_page":"4175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11321","display_name":"Error Correcting Code Techniques","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11321","display_name":"Error Correcting Code Techniques","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10964","display_name":"Wireless Communication Security Techniques","score":0.9990000128746033,"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/T12029","display_name":"DNA and Biological Computing","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7667355537414551},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6270424127578735},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6251313090324402},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.566435694694519},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5634042024612427},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5318832993507385},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33901911973953247},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26663002371788025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12237387895584106},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.06114169955253601}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7667355537414551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6270424127578735},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6251313090324402},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.566435694694519},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5634042024612427},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5318832993507385},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33901911973953247},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26663002371788025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12237387895584106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.06114169955253601},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc60939.2024.10645022","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc60939.2024.10645022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1496184890","https://openalex.org/W1557517019","https://openalex.org/W1978595443","https://openalex.org/W1990949042","https://openalex.org/W2010654234","https://openalex.org/W2113846837","https://openalex.org/W2116343044","https://openalex.org/W2128823230","https://openalex.org/W2133966244","https://openalex.org/W2164684058","https://openalex.org/W2168228312","https://openalex.org/W2258043381","https://openalex.org/W2963922350","https://openalex.org/W2964034900","https://openalex.org/W2998102890","https://openalex.org/W3016715915","https://openalex.org/W3047409223","https://openalex.org/W3102156549","https://openalex.org/W3105388688","https://openalex.org/W3136541527","https://openalex.org/W3136561982","https://openalex.org/W3205387731","https://openalex.org/W4250389103","https://openalex.org/W4287640641","https://openalex.org/W4302366875","https://openalex.org/W4313387453","https://openalex.org/W4385900824","https://openalex.org/W4391021929","https://openalex.org/W4399728557","https://openalex.org/W6784034564"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340"],"abstract_inverted_index":{"We":[0,52,100],"study":[1],"the":[2,25,34,69,74,91,96],"problem":[3,26,94],"of":[4,7,47,80],"zero-delay":[5,92],"coding":[6,93],"a":[8,12,28,37,44,112],"Markov":[9,29],"source":[10],"over":[11,59],"noisy":[13],"channel":[14,48],"with":[15,43],"feedback.":[16],"Building":[17],"and":[18,50,110,116],"generalizing":[19],"prior":[20],"work,":[21],"we":[22,83],"first":[23],"formulate":[24],"as":[27,95],"decision":[30],"process":[31],"(MDP)":[32],"where":[33],"state":[35,56],"is":[36],"probability":[38],"measure":[39],"valued":[40],"predictor":[41,81,106],"along":[42],"finite":[45],"memory":[46,97],"outputs":[49],"quantizers.":[51],"then":[53],"approximate":[54],"this":[55],"by":[57,130],"marginalizing":[58],"all":[60],"possible":[61],"predictors,":[62],"so":[63],"that":[64,85],"our":[65],"policies":[66,87],"only":[67],"use":[68],"finite-memory":[70,123],"term":[71],"to":[72,108,120],"encode":[73],"source.":[75],"Under":[76],"an":[77],"appropriate":[78],"notion":[79],"stability,":[82],"show":[84],"such":[86],"are":[88,128],"near-optimal":[89,122],"for":[90,105],"length":[98],"increases.":[99],"also":[101],"give":[102],"sufficient":[103],"conditions":[104],"stability":[107],"hold,":[109],"present":[111],"reinforcement":[113],"learning":[114],"algorithm":[115],"establish":[117],"its":[118],"convergence":[119],"compute":[121],"policies.":[124],"These":[125],"theoretical":[126],"results":[127],"supported":[129],"simulations.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}