{"id":"https://openalex.org/W2724896429","doi":"https://doi.org/10.1109/icis.2017.7960020","title":"Cooperative multi-agent reinforcement learning in a large stationary environment","display_name":"Cooperative multi-agent reinforcement learning in a large stationary environment","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2724896429","doi":"https://doi.org/10.1109/icis.2017.7960020","mag":"2724896429"},"language":"en","primary_location":{"id":"doi:10.1109/icis.2017.7960020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icis.2017.7960020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS)","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/A5003898668","display_name":"Wiem Zemzem","orcid":null},"institutions":[{"id":"https://openalex.org/I83259278","display_name":"Manouba University","ror":"https://ror.org/0503ejf32","country_code":"TN","type":"education","lineage":["https://openalex.org/I83259278"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Wiem Zemzem","raw_affiliation_strings":["National School of Computer Science, University of Manouba, Tunisia"],"affiliations":[{"raw_affiliation_string":"National School of Computer Science, University of Manouba, Tunisia","institution_ids":["https://openalex.org/I83259278"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036389154","display_name":"Moncef Tagina","orcid":null},"institutions":[{"id":"https://openalex.org/I83259278","display_name":"Manouba University","ror":"https://ror.org/0503ejf32","country_code":"TN","type":"education","lineage":["https://openalex.org/I83259278"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Moncef Tagina","raw_affiliation_strings":["National School of Computer Science, University of Manouba, Tunisia"],"affiliations":[{"raw_affiliation_string":"National School of Computer Science, University of Manouba, Tunisia","institution_ids":["https://openalex.org/I83259278"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003898668"],"corresponding_institution_ids":["https://openalex.org/I83259278"],"apc_list":null,"apc_paid":null,"fwci":0.195,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6077105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"7006","issue":null,"first_page":"365","last_page":"371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9937999844551086,"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":0.9929999709129333,"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":0.8798031806945801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7566021084785461},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7051447629928589},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.6799041032791138},{"id":"https://openalex.org/keywords/foraging","display_name":"Foraging","score":0.5851759314537048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5788708925247192},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5084692239761353},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.4246925115585327},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4113267660140991},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13937988877296448}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8798031806945801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566021084785461},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7051447629928589},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.6799041032791138},{"id":"https://openalex.org/C165287380","wikidata":"https://www.wikidata.org/wiki/Q2916569","display_name":"Foraging","level":2,"score":0.5851759314537048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5788708925247192},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5084692239761353},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4246925115585327},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4113267660140991},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13937988877296448},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icis.2017.7960020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icis.2017.7960020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41159429","https://openalex.org/W1487219635","https://openalex.org/W1488799533","https://openalex.org/W1504212531","https://openalex.org/W1510994837","https://openalex.org/W1554233645","https://openalex.org/W1744965757","https://openalex.org/W2058412232","https://openalex.org/W2107544712","https://openalex.org/W2115524942","https://openalex.org/W2121517924","https://openalex.org/W2145521109","https://openalex.org/W2293337064","https://openalex.org/W2895974005","https://openalex.org/W4214717370","https://openalex.org/W4214807090","https://openalex.org/W6629128764","https://openalex.org/W6630225054","https://openalex.org/W6630732992","https://openalex.org/W6637659587","https://openalex.org/W6681489846"],"related_works":["https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2912947802","https://openalex.org/W2037601570","https://openalex.org/W2123856982","https://openalex.org/W1530089576","https://openalex.org/W2371091044","https://openalex.org/W87513465","https://openalex.org/W2786230833"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,16,30,54],"comprises":[2],"an":[3],"attractive":[4],"solution":[5],"to":[6,12,28,32,40],"the":[7,52,63,92,98],"multi-agent":[8],"cooperation":[9],"problem,":[10],"due":[11],"its":[13],"robustness":[14],"for":[15],"in":[17,38,47,57,97],"unknown":[18,102],"and":[19,103],"uncertain":[20],"environments.":[21,105],"The":[22,87],"objective":[23],"of":[24,35,65,94,100],"this":[25,66],"paper":[26],"is":[27,59,84],"provide":[29],"capabilities":[31],"a":[33,43,48],"group":[34],"autonomous":[36],"agents":[37],"order":[39],"efficiently":[41],"perform":[42],"cooperative":[44,69],"foraging":[45],"task":[46],"distributed":[49],"manner.":[50],"Firstly,":[51],"D-DCM-MultiQ":[53],"method,":[55,67],"presented":[56],"[1],":[58],"evaluated.":[60],"To":[61],"overcome":[62],"shortcomings":[64],"new":[68,76],"action":[70],"selection":[71],"strategies":[72],"are":[73],"developed.":[74],"A":[75],"exploration":[77],"alternative,":[78],"favoring":[79],"least":[80],"recently":[81],"visited":[82],"states,":[83],"also":[85],"proposed.":[86],"conducted":[88],"simulation":[89],"tests":[90],"indicate":[91],"efficiency":[93],"suggested":[95],"improvements":[96],"case":[99],"large,":[101],"stationary":[104]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}