{"id":"https://openalex.org/W3106696947","doi":"https://doi.org/10.1109/icce-taiwan49838.2020.9258271","title":"Position-Aware Communication via Self-Attention for Multi-Agent Reinforcement Learning","display_name":"Position-Aware Communication via Self-Attention for Multi-Agent Reinforcement Learning","publication_year":2020,"publication_date":"2020-09-28","ids":{"openalex":"https://openalex.org/W3106696947","doi":"https://doi.org/10.1109/icce-taiwan49838.2020.9258271","mag":"3106696947"},"language":"en","primary_location":{"id":"doi:10.1109/icce-taiwan49838.2020.9258271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-taiwan49838.2020.9258271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","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/A5012580757","display_name":"Tsan-Hua Shih","orcid":null},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Tsan-Hua Shih","raw_affiliation_strings":["Graduate Institute of Automation Technology, National Taipei University of Technology, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Automation Technology, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086104885","display_name":"Hsien-I Lin","orcid":"https://orcid.org/0000-0002-6195-3353"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsien-I Lin","raw_affiliation_strings":["Graduate Institute of Automation Technology, National Taipei University of Technology, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Automation Technology, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012580757"],"corresponding_institution_ids":["https://openalex.org/I118292597"],"apc_list":null,"apc_paid":null,"fwci":0.1542,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53983014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 1507 6527","issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","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/T10249","display_name":"Distributed Control Multi-Agent Systems","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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9940000176429749,"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":0.8032684922218323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.679612398147583},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.6194692254066467},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5094309449195862},{"id":"https://openalex.org/keywords/position-paper","display_name":"Position paper","score":0.4970245659351349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3804089426994324},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3763059377670288},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15081405639648438},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09929540753364563},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0744304358959198}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8032684922218323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.679612398147583},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.6194692254066467},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5094309449195862},{"id":"https://openalex.org/C78780964","wikidata":"https://www.wikidata.org/wiki/Q7233193","display_name":"Position paper","level":2,"score":0.4970245659351349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3804089426994324},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3763059377670288},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15081405639648438},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09929540753364563},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0744304358959198},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce-taiwan49838.2020.9258271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-taiwan49838.2020.9258271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2096145798","https://openalex.org/W2121092017","https://openalex.org/W2395575420","https://openalex.org/W2626637010","https://openalex.org/W2803155336","https://openalex.org/W2962938178","https://openalex.org/W2963403868","https://openalex.org/W2963937357","https://openalex.org/W2964338167","https://openalex.org/W4297789683","https://openalex.org/W4299802797","https://openalex.org/W4385245566","https://openalex.org/W6677939520","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6743367460","https://openalex.org/W6751139674"],"related_works":["https://openalex.org/W2911039683","https://openalex.org/W2382416307","https://openalex.org/W2169127058","https://openalex.org/W1966415008","https://openalex.org/W3112644326","https://openalex.org/W4389316227","https://openalex.org/W2204729203","https://openalex.org/W2187575493","https://openalex.org/W2203842767","https://openalex.org/W2389520089"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2],"is":[3,9,17,67,73,87,100,115],"important":[4],"for":[5,111],"real-world":[6],"applications":[7],"but":[8,80],"still":[10],"a":[11,25,42,103,108],"challenging":[12],"problem.":[13],"A":[14],"feasible":[15],"way":[16],"to":[18,36],"share":[19],"information":[20,39,128],"among":[21],"all":[22],"agents":[23],"via":[24,129],"communication":[26,32,109],"channel.":[27],"In":[28,90,122,132],"recent":[29],"years,":[30],"attentional":[31,49],"emerged":[33],"in":[34,85,140],"order":[35],"differentiate":[37],"valuable":[38],"especially":[40],"with":[41,59,145],"large":[43],"number":[44],"of":[45,71,78,117,120,142],"agents.":[46,121],"However,":[47],"existing":[48,146],"communication,":[50],"which":[51,99],"relies":[52],"on":[53,75],"long":[54],"short-term":[55],"memory":[56],"(LSTM)":[57],"units":[58],"attention":[60],"mechanism,":[61],"makes":[62],"parallelization":[63],"difficult.":[64],"Another":[65],"problem":[66],"that":[68],"the":[69,76,81,118,135],"output":[70],"LSTM":[72],"dependent":[74],"sequence":[77,119],"agents,":[79,84],"relationship":[82],"between":[83],"general,":[86],"not":[88],"sequential.":[89],"this":[91],"paper,":[92],"we":[93,124],"proposed":[94,101,136],"using":[95],"multi-head":[96],"self-attention":[97],"layer,":[98],"from":[102],"well-known":[104],"net":[105],"\u201cTransformer\u201d,":[106],"as":[107],"channel":[110],"parallelization.":[112],"Attention":[113],"mechanism":[114],"independent":[116],"addition,":[123],"also":[125],"incorporate":[126],"position":[127],"positional":[130],"encoding.":[131],"our":[133],"experiments,":[134],"method":[137],"achieves":[138],"improvements":[139],"terms":[141],"reward":[143],"compared":[144],"approaches.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}