{"id":"https://openalex.org/W2568887908","doi":"https://doi.org/10.1109/cdc.2016.7799442","title":"Large-scale multi-agent reinforcement learning using image-based state representation","display_name":"Large-scale multi-agent reinforcement learning using image-based state representation","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2568887908","doi":"https://doi.org/10.1109/cdc.2016.7799442","mag":"2568887908"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2016.7799442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7799442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","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/A5101737502","display_name":"Tianshu Chu","orcid":"https://orcid.org/0000-0002-9404-3348"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianshu Chu","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112694715","display_name":"Shuhui Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuhui Qu","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072667046","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0001-5500-2060"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101737502"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.3331,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.880763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7592","last_page":"7597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9919999837875366,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.98580002784729,"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":0.8402431011199951},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.70628422498703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.606210470199585},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5605207085609436},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5431349873542786},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.536291778087616},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4906400740146637},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44642236828804016},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4301029443740845},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.42232292890548706},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42005330324172974},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.323810338973999},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.24068239331245422},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.177240252494812}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8402431011199951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.70628422498703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.606210470199585},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5605207085609436},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5431349873542786},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.536291778087616},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4906400740146637},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44642236828804016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4301029443740845},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42232292890548706},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42005330324172974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.323810338973999},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.24068239331245422},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.177240252494812},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2016.7799442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7799442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","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":35,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W33871791","https://openalex.org/W1547105496","https://openalex.org/W1550698229","https://openalex.org/W1588304026","https://openalex.org/W1757796397","https://openalex.org/W1982262386","https://openalex.org/W2027628482","https://openalex.org/W2076337359","https://openalex.org/W2103561211","https://openalex.org/W2110906765","https://openalex.org/W2118318536","https://openalex.org/W2120346334","https://openalex.org/W2134779831","https://openalex.org/W2139418546","https://openalex.org/W2141559645","https://openalex.org/W2147768505","https://openalex.org/W2152430560","https://openalex.org/W2163605009","https://openalex.org/W2164278908","https://openalex.org/W2168405694","https://openalex.org/W2257979135","https://openalex.org/W2404646363","https://openalex.org/W4245296547","https://openalex.org/W4292363360","https://openalex.org/W4298857966","https://openalex.org/W6635209275","https://openalex.org/W6637967152","https://openalex.org/W6675356487","https://openalex.org/W6676769901","https://openalex.org/W6677737365","https://openalex.org/W6677834374","https://openalex.org/W6680096503","https://openalex.org/W6682809161","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W4287776258","https://openalex.org/W3027997911","https://openalex.org/W2767651786","https://openalex.org/W3021430260","https://openalex.org/W2912288872","https://openalex.org/W564581980","https://openalex.org/W4319083788","https://openalex.org/W3106036237","https://openalex.org/W2546942002","https://openalex.org/W2970216048"],"abstract_inverted_index":{"With":[0],"its":[1],"high-dimensional":[2,64],"state":[3],"and":[4,44,92,123,146,197],"action":[5,137],"space,":[6],"large-scale":[7,199],"multi-agent":[8,47],"reinforcement":[9],"learning":[10,144,203],"(MARL)":[11],"is":[12,19],"a":[13,71,78,111,149,177],"challenging":[14],"problem.":[15],"Centralized":[16],"approximate":[17],"RL":[18,62,163],"impractical":[20],"to":[21,170,195],"deal":[22],"with":[23,31,63],"this":[24,106,108,161],"because":[25],"the":[26,32,68,82,93,99,135,140,143,171,188],"search":[27,133],"cost":[28],"grows":[29],"exponentially":[30],"number":[33],"of":[34,70,80,142],"agents.":[35],"Further,":[36],"traditional":[37,172],"decentralized":[38,132],"approaches":[39],"require":[40],"delicate":[41],"model-specific":[42],"decomposition":[43],"communication":[45],"within":[46],"system":[48],"(MAS).":[49],"Recently,":[50],"however,":[51],"convolutional":[52],"neural":[53],"network":[54],"(CNN)":[55],"has":[56,165],"been":[57],"successfully":[58],"integrated":[59],"into":[60],"perceptional":[61],"input":[65],"images.":[66],"If":[67],"information":[69],"MAS":[72],"can":[73,191],"also":[74],"be":[75,86],"recorded":[76],"by":[77,89,117],"stack":[79],"images,":[81],"spatial":[83],"correlation":[84],"would":[85],"naturally":[87],"represented":[88],"`pixel'":[90],"positions":[91],"kernel":[94],"filter":[95],"that":[96,160,187],"allows":[97],"for":[98,115,120,126,134,154],"multi-scale":[100],"communications":[101],"in":[102],"MAS.":[103],"Based":[104],"on":[105,139],"observation,":[107],"paper":[109],"proposes":[110],"new":[112],"image-based":[113,189],"representation":[114,190],"MARL":[116,200],"combining":[118],"CNN":[119],"feature":[121,181],"extraction":[122],"linear":[124],"regression":[125],"Q-function":[127],"approximation.":[128],"Additionally,":[129],"we":[130],"perform":[131],"optimal":[136],"based":[138],"structure":[141],"model,":[145],"then":[147],"propose":[148],"distributed":[150],"fitted":[151],"Q-iteration":[152],"framework":[153],"general-purpose":[155],"MARL.":[156],"Initial":[157],"experiments":[158],"demonstrate":[159,186],"CNN-enhanced":[162],"agent":[164],"competitive":[166],"performance":[167],"when":[168],"compared":[169],"ones,":[173],"which":[174],"learn":[175],"from":[176],"manually":[178],"designed":[179],"flat":[180],"representation.":[182],"These":[183],"encouraging":[184],"results":[185],"provide":[192],"promising":[193],"opportunities":[194],"represent":[196],"analyze":[198],"using":[201],"deep":[202],"techniques.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}