{"id":"https://openalex.org/W2024605041","doi":"https://doi.org/10.1109/coginf.2010.5599681","title":"Reinforcement learning for multi-agent patrol policy","display_name":"Reinforcement learning for multi-agent patrol policy","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2024605041","doi":"https://doi.org/10.1109/coginf.2010.5599681","mag":"2024605041"},"language":"en","primary_location":{"id":"doi:10.1109/coginf.2010.5599681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginf.2010.5599681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th IEEE International Conference on Cognitive Informatics (ICCI'10)","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/A5103026744","display_name":"Zhaohui Hu","orcid":"https://orcid.org/0000-0002-2793-2145"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaohui Hu","raw_affiliation_strings":["Lab of Complex Systems and Intelligence Sciences, Institute of Automation, Chinese Academy and Sciences, Beijing, China","Lab. of Complex Systems and Intelligence Sciences, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, china"],"affiliations":[{"raw_affiliation_string":"Lab of Complex Systems and Intelligence Sciences, Institute of Automation, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"Lab. of Complex Systems and Intelligence Sciences, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, china","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["Lab of Complex Systems and Intelligence Sciences, Institute of Automation, Chinese Academy and Sciences, Beijing, China","Lab. of Complex Systems and Intelligence Sciences, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, china"],"affiliations":[{"raw_affiliation_string":"Lab of Complex Systems and Intelligence Sciences, Institute of Automation, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"Lab. of Complex Systems and Intelligence Sciences, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, china","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103026744"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":1.0684,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.77756636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"8","issue":null,"first_page":"530","last_page":"535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9947999715805054,"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/T12288","display_name":"Optimization and Search Problems","score":0.9947999715805054,"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/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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9927999973297119,"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/softmax-function","display_name":"Softmax function","score":0.9082000255584717},{"id":"https://openalex.org/keywords/patrolling","display_name":"Patrolling","score":0.8916386365890503},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8798712491989136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7411210536956787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5259000658988953},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4672781229019165},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4649229347705841},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.458418071269989},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1306731104850769},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12154191732406616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10146129131317139}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9082000255584717},{"id":"https://openalex.org/C110698143","wikidata":"https://www.wikidata.org/wiki/Q651389","display_name":"Patrolling","level":2,"score":0.8916386365890503},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8798712491989136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411210536956787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5259000658988953},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4672781229019165},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4649229347705841},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.458418071269989},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1306731104850769},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12154191732406616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10146129131317139},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coginf.2010.5599681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginf.2010.5599681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th IEEE International Conference on Cognitive Informatics (ICCI'10)","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":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W52443889","https://openalex.org/W1543672909","https://openalex.org/W1622701847","https://openalex.org/W1964839117","https://openalex.org/W2007572995","https://openalex.org/W2095671661","https://openalex.org/W2104863707","https://openalex.org/W2108950458","https://openalex.org/W2121863487","https://openalex.org/W2128862550","https://openalex.org/W2155511526","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6604969303","https://openalex.org/W6632495983","https://openalex.org/W6675981125","https://openalex.org/W6679022538","https://openalex.org/W6683093126"],"related_works":["https://openalex.org/W170273588","https://openalex.org/W2337788814","https://openalex.org/W2092973197","https://openalex.org/W2163146706","https://openalex.org/W2404411151","https://openalex.org/W3206391274","https://openalex.org/W167683769","https://openalex.org/W2332242917","https://openalex.org/W2095900292","https://openalex.org/W2374340569"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,18],"reinforcement":[4],"learning":[5],"(RL)":[6],"algorithm":[7,105],"for":[8,108,138],"multi-agent":[9,34],"patrol":[10,57,123],"tasks,":[11],"which":[12,70],"can":[13],"be":[14],"thought":[15],"of":[16,61],"as":[17,30,41,51],"dynamic":[19],"programming":[20],"problem":[21,63],"with":[22,126,145],"stochastic":[23],"demands.":[24],"We":[25,110],"define":[26],"the":[27,31,33,42,45,49,52,56,72,82,94,99,122,134],"cover":[28,124],"rate":[29,125],"reward,":[32],"physical":[35],"positions":[36],"including":[37],"edges":[38],"and":[39,44,74,97,117,133],"nodes":[40,46],"state,":[43],"adjacent":[47],"to":[48,54,87,92,148],"agent":[50],"action":[53],"model":[55],"task.":[58],"The":[59],"modeling":[60],"this":[62],"is":[64,106,141],"totally":[65],"different":[66],"from":[67,84],"other's":[68],"work,":[69],"facilitates":[71],"communication":[73],"cooperation":[75],"among":[76],"these":[77],"agents.":[78],"Furthermore,":[79],"we":[80],"map":[81],"state":[83],"four":[85],"dimensions":[86],"one":[88],"dimension":[89],"in":[90,115],"order":[91],"improve":[93],"training":[95],"efficiency":[96],"reduce":[98],"coding":[100],"complexity.":[101],"A":[102],"deterministic":[103],"Softmax":[104,130],"designed":[107],"comparison.":[109],"test":[111],"both":[112],"two":[113],"algorithms":[114],"patrolling":[116],"rescuing":[118],"scenarios.":[119],"Results":[120],"show":[121],"RL":[127,146],"greatly":[128],"outperforms":[129],"about":[131],"15.38%,":[132],"average":[135],"rescue":[136],"time":[137],"emergent":[139],"pots":[140],"reduced":[142],"by":[143],"20%":[144],"compared":[147],"Softmax.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}