{"id":"https://openalex.org/W4405103452","doi":"https://doi.org/10.1109/milcom61039.2024.10773737","title":"Reinforcement Learning over Noisy Channels: An Information Bottleneck Approach","display_name":"Reinforcement Learning over Noisy Channels: An Information Bottleneck Approach","publication_year":2024,"publication_date":"2024-10-28","ids":{"openalex":"https://openalex.org/W4405103452","doi":"https://doi.org/10.1109/milcom61039.2024.10773737"},"language":"en","primary_location":{"id":"doi:10.1109/milcom61039.2024.10773737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom61039.2024.10773737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2024 - 2024 IEEE Military Communications Conference (MILCOM)","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/A5028205966","display_name":"Clement Kam","orcid":"https://orcid.org/0000-0001-5439-1199"},"institutions":[{"id":"https://openalex.org/I1288214837","display_name":"United States Naval Research Laboratory","ror":"https://ror.org/04d23a975","country_code":"US","type":"facility","lineage":["https://openalex.org/I1288214837","https://openalex.org/I1330347796","https://openalex.org/I175003984","https://openalex.org/I3130687028"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Clement Kam","raw_affiliation_strings":["U.S. Naval Research Laboratory,Information Technology Division,Washington, DC,USA"],"affiliations":[{"raw_affiliation_string":"U.S. Naval Research Laboratory,Information Technology Division,Washington, DC,USA","institution_ids":["https://openalex.org/I1288214837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112733653","display_name":"Joseph P. Macker","orcid":null},"institutions":[{"id":"https://openalex.org/I1288214837","display_name":"United States Naval Research Laboratory","ror":"https://ror.org/04d23a975","country_code":"US","type":"facility","lineage":["https://openalex.org/I1288214837","https://openalex.org/I1330347796","https://openalex.org/I175003984","https://openalex.org/I3130687028"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph P. Macker","raw_affiliation_strings":["U.S. Naval Research Laboratory,Information Technology Division,Washington, DC,USA"],"affiliations":[{"raw_affiliation_string":"U.S. Naval Research Laboratory,Information Technology Division,Washington, DC,USA","institution_ids":["https://openalex.org/I1288214837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003200620","display_name":"Yin Sun","orcid":"https://orcid.org/0000-0001-6811-984X"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yin Sun","raw_affiliation_strings":["Auburn University,Dept. of ECE,Auburn,AL,USA"],"affiliations":[{"raw_affiliation_string":"Auburn University,Dept. of ECE,Auburn,AL,USA","institution_ids":["https://openalex.org/I82497590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028205966"],"corresponding_institution_ids":["https://openalex.org/I1288214837"],"apc_list":null,"apc_paid":null,"fwci":0.222,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5589027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9957000017166138,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9957000017166138,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9919000267982483,"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/T10320","display_name":"Neural Networks and Applications","score":0.9886000156402588,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8469060659408569},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7581976056098938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6873314380645752},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.49687913060188293},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4201880693435669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37963035702705383},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11946263909339905},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0931781530380249}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8469060659408569},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7581976056098938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6873314380645752},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.49687913060188293},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4201880693435669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37963035702705383},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11946263909339905},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0931781530380249},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/milcom61039.2024.10773737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom61039.2024.10773737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2024 - 2024 IEEE Military Communications Conference (MILCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4399999976158142,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W3107013237","https://openalex.org/W3206195449","https://openalex.org/W3214462705","https://openalex.org/W4297882599","https://openalex.org/W4395686776","https://openalex.org/W6637108112","https://openalex.org/W6717305147","https://openalex.org/W6729906282","https://openalex.org/W6737350872","https://openalex.org/W6767141496","https://openalex.org/W6770332567","https://openalex.org/W6782248096","https://openalex.org/W6786286809","https://openalex.org/W6790944140"],"related_works":["https://openalex.org/W4401325445","https://openalex.org/W2622284819","https://openalex.org/W1504394672","https://openalex.org/W3089381707","https://openalex.org/W4285254085","https://openalex.org/W3034190530","https://openalex.org/W2741297526","https://openalex.org/W4295728955","https://openalex.org/W3129794609","https://openalex.org/W2949033103"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,103],"study":[4],"reinforcement":[5,63],"learning":[6,64,93],"(RL)":[7],"in":[8,14,37],"a":[9,16,27,30,47],"remote":[10],"control":[11],"wireless":[12],"setting,":[13],"which":[15,32,79],"transmitter":[17],"observes":[18],"the":[19,38,42,55,59,68,75,85,88,92,96,110,114,119,129,133],"state":[20],"of":[21,61,87,109,128],"an":[22,35,105],"environment,":[23],"processes":[24],"and":[25,77,113,122,136],"transmits":[26],"message":[28,57],"to":[29,51,73,83],"receiver,":[31],"then":[33],"takes":[34],"action":[36],"environment":[39],"based":[40],"on":[41],"received":[43],"message.":[44],"We":[45,66],"take":[46],"goal-oriented":[48],"communications":[49],"approach":[50,72,112],"encoding":[52],"(and":[53],"decoding)":[54],"transmitted":[56],"with":[58,91],"purpose":[60],"maximizing":[62],"performance.":[65,94],"apply":[67],"information":[69,106],"bottleneck":[70,134],"(IB)":[71],"training":[74,120],"encoder":[76],"decoder,":[78],"uses":[80],"information-theoretic":[81],"concepts":[82],"balance":[84],"compression":[86],"input":[89],"data":[90],"Using":[95],"familiar":[97],"deep":[98],"Q-network":[99],"(DQN)":[100],"RL":[101],"approach,":[102],"provide":[104],"theoretic":[107],"interpretation":[108],"IB":[111,130],"noisy":[115],"channel.":[116],"Simulations":[117],"demonstrate":[118],"performance":[121,124],"generalization":[123],"under":[125],"various":[126],"settings":[127],"tradeoff":[131],"parameter,":[132],"dimension,":[135],"channel":[137],"noise.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}