{"id":"https://openalex.org/W4385694588","doi":"https://doi.org/10.1109/ssp53291.2023.10207979","title":"Semantic Communication for Partial Observation Multi-agent Reinforcement Learning","display_name":"Semantic Communication for Partial Observation Multi-agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-07-02","ids":{"openalex":"https://openalex.org/W4385694588","doi":"https://doi.org/10.1109/ssp53291.2023.10207979"},"language":"en","primary_location":{"id":"doi:10.1109/ssp53291.2023.10207979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssp53291.2023.10207979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","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/A5044235490","display_name":"Hoang Khoi","orcid":"https://orcid.org/0000-0002-2566-5637"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hoang Khoi Do","raw_affiliation_strings":["HUST,School of Electrical and Electronic Engineering,Hanoi,Vietnam","School of Electrical and Electronic Engineering, HUST, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HUST,School of Electrical and Electronic Engineering,Hanoi,Vietnam","institution_ids":[]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, HUST, Hanoi, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072687861","display_name":"Thi Quynh Dinh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thi Quynh Dinh","raw_affiliation_strings":["HUST,School of Electrical and Electronic Engineering,Hanoi,Vietnam","School of Electrical and Electronic Engineering, HUST, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HUST,School of Electrical and Electronic Engineering,Hanoi,Vietnam","institution_ids":[]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, HUST, Hanoi, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432921","display_name":"Minh Nguyen","orcid":"https://orcid.org/0000-0003-0106-9715"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minh Duong Nguyen","raw_affiliation_strings":["Pusan National University,Department of Information Convergence Engineering,Pusan,Republic of Korea,46241"],"affiliations":[{"raw_affiliation_string":"Pusan National University,Department of Information Convergence Engineering,Pusan,Republic of Korea,46241","institution_ids":["https://openalex.org/I4921948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050879879","display_name":"Ti\u1ebfn Hoa Nguy\u1ec5n","orcid":"https://orcid.org/0000-0003-4743-5012"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tien Hoa Nguyen","raw_affiliation_strings":["HUST,School of Electrical and Electronic Engineering,Hanoi,Vietnam","School of Electrical and Electronic Engineering, HUST, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HUST,School of Electrical and Electronic Engineering,Hanoi,Vietnam","institution_ids":[]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, HUST, Hanoi, Vietnam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044235490"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64818037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.994700014591217,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9912999868392944,"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":0.8118009567260742},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7737289667129517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5034946799278259},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4366755187511444},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3635016977787018}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8118009567260742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7737289667129517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034946799278259},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4366755187511444},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3635016977787018}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssp53291.2023.10207979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssp53291.2023.10207979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1936503582","https://openalex.org/W1974812331","https://openalex.org/W2108005621","https://openalex.org/W2395575420","https://openalex.org/W2520157010","https://openalex.org/W2539402368","https://openalex.org/W2591957553","https://openalex.org/W2736601468","https://openalex.org/W2913602408","https://openalex.org/W2914304175","https://openalex.org/W2929242575","https://openalex.org/W2980001345","https://openalex.org/W2982316857","https://openalex.org/W3036086835","https://openalex.org/W3090386093","https://openalex.org/W3101889877","https://openalex.org/W3156295478","https://openalex.org/W4205331573","https://openalex.org/W4226490931","https://openalex.org/W4289363497","https://openalex.org/W4301501993","https://openalex.org/W4317382091","https://openalex.org/W6622433990","https://openalex.org/W6630029800","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6728155968","https://openalex.org/W6741002519","https://openalex.org/W6755542948","https://openalex.org/W6779257429","https://openalex.org/W6783838878","https://openalex.org/W6796861069","https://openalex.org/W6800131325","https://openalex.org/W6810168854"],"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/W3204019825"],"abstract_inverted_index":{"Effective":[0],"cooperation":[1],"and":[2,65,90,119,123],"coordination":[3,89],"among":[4],"agents":[5,23,57,72,80,108],"is":[6],"essential":[7],"for":[8,87,135],"success":[9],"in":[10,15,141],"many":[11],"real-world":[12],"scenarios,":[13],"particularly":[14],"reinforcement":[16,143],"learning":[17],"challenges.":[18],"However,":[19],"partial":[20,138],"observation,":[21],"where":[22],"are":[24],"not":[25,113],"aware":[26],"of":[27,78,97,121],"all":[28],"the":[29,47,76,116,137],"observations":[30,64,77,99,118],"made":[31],"by":[32],"other":[33,79],"agents,":[34],"creates":[35],"a":[36,132],"significant":[37],"obstacle":[38],"to":[39,58,60,74,81],"coordination.":[40],"To":[41],"overcome":[42],"this":[43],"challenge,":[44],"we":[45],"propose":[46],"Shared":[48],"Online":[49],"Multi-agent":[50],"Knowledge":[51],"Exchange":[52],"(SOME)":[53],"framework,":[54],"which":[55],"allows":[56],"learn":[59,73],"anticipate":[61,75],"each":[62],"other\u2019s":[63],"improve":[66,82],"their":[67,83],"local":[68,84],"learning.":[69,144],"In":[70],"SOME,":[71],"learning,":[85],"allowing":[86],"better":[88],"cooperation.":[91],"Additionally,":[92],"using":[93],"knowledge":[94],"generators":[95],"instead":[96],"full":[98],"reduces":[100],"communication":[101],"costs.":[102],"Our":[103],"experimental":[104],"evaluation":[105],"demonstrates":[106],"that":[107],"trained":[109],"with":[110],"SOME":[111],"can":[112],"only":[114],"predict":[115],"next":[117],"actions":[120],"opponents":[122],"collaborators":[124],"but":[125],"also":[126],"take":[127],"appropriate":[128],"actions,":[129],"making":[130],"it":[131],"promising":[133],"approach":[134],"overcoming":[136],"observation":[139],"challenge":[140],"multi-agent":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}