{"id":"https://openalex.org/W2162022118","doi":"https://doi.org/10.1109/adprl.2013.6614989","title":"A combined hierarchical reinforcement learning based approach for multi-robot cooperative target searching in complex unknown environments","display_name":"A combined hierarchical reinforcement learning based approach for multi-robot cooperative target searching in complex unknown environments","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W2162022118","doi":"https://doi.org/10.1109/adprl.2013.6614989","mag":"2162022118"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2013.6614989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6614989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5088215418","display_name":"Yifan Cai","orcid":"https://orcid.org/0000-0002-2552-0964"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Yifan Cai","raw_affiliation_strings":["The School of Engineering, University of Guelph, Guelph, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"The School of Engineering, University of Guelph, Guelph, Ontario, Canada","institution_ids":["https://openalex.org/I79817857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029827598","display_name":"Simon X. Yang","orcid":"https://orcid.org/0000-0002-6888-7993"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Simon X. Yang","raw_affiliation_strings":["The School of Engineering, University of Guelph, Guelph, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"The School of Engineering, University of Guelph, Guelph, Ontario, Canada","institution_ids":["https://openalex.org/I79817857"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["The College of Mechatronics and Automation, National University of Defense Technology, Changsha, Hunan Province, China"],"affiliations":[{"raw_affiliation_string":"The College of Mechatronics and Automation, National University of Defense Technology, Changsha, Hunan Province, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088215418"],"corresponding_institution_ids":["https://openalex.org/I79817857"],"apc_list":null,"apc_paid":null,"fwci":2.8856,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91856803,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8236401677131653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8099454045295715},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7435528039932251},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.7138338685035706},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6520901918411255},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5961712002754211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5448246002197266},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4187510013580322},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38977810740470886},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08167821168899536}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8236401677131653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8099454045295715},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7435528039932251},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7138338685035706},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6520901918411255},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5961712002754211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5448246002197266},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4187510013580322},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38977810740470886},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08167821168899536},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2013.6614989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6614989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1488730473","https://openalex.org/W1515436326","https://openalex.org/W1568042657","https://openalex.org/W1986610177","https://openalex.org/W1989665358","https://openalex.org/W2054040837","https://openalex.org/W2059539888","https://openalex.org/W2109910161","https://openalex.org/W2111616957","https://openalex.org/W2115220039","https://openalex.org/W2129853306","https://openalex.org/W2130439666","https://openalex.org/W2132862210","https://openalex.org/W2733397824","https://openalex.org/W4214717370","https://openalex.org/W6629152578","https://openalex.org/W6664164167","https://openalex.org/W6740605839"],"related_works":["https://openalex.org/W2365264209","https://openalex.org/W4306904969","https://openalex.org/W962203960","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2026999166","https://openalex.org/W2024136090","https://openalex.org/W2967461658"],"abstract_inverted_index":{"Effective":[0],"cooperation":[1,33,40,65,85,94],"of":[2,41,123],"multi-robots":[3,42],"in":[4,9,43,131],"unknown":[5,45,133],"environments":[6],"is":[7,35,87,114],"essential":[8],"many":[10],"robotic":[11],"applications,":[12],"such":[13],"as":[14],"environment":[15,54],"exploration":[16],"and":[17,61,118],"target":[18,128],"searching.":[19],"In":[20,89],"this":[21],"paper,":[22],"a":[23,31,121],"combined":[24],"hierarchical":[25],"reinforcement":[26],"learning":[27],"approach,":[28],"together":[29],"with":[30,79],"designed":[32,93],"strategy,":[34],"proposed":[36,64,112],"for":[37],"the":[38,63,69,80,84,92,98,103,111],"real-time":[39],"completely":[44,132],"environments.":[46,134],"Unlike":[47],"other":[48],"algorithms":[49],"that":[50,110],"need":[51],"an":[52],"explicit":[53],"model":[55],"or":[56],"select":[57],"parameters":[58,71],"by":[59],"trial":[60],"error,":[62],"method":[66,95],"obtains":[67],"all":[68],"required":[70],"automatically":[72],"through":[73],"learning.":[74],"By":[75],"integrating":[76],"segmental":[77],"options":[78],"traditional":[81],"MAXQ":[82],"algorithm,":[83],"hierarchy":[86],"built.":[88],"new":[90],"tasks,":[91],"can":[96],"control":[97],"multi-robot":[99],"system":[100],"to":[101,116,125],"complete":[102],"task":[104],"effectively.":[105],"The":[106],"simulation":[107],"results":[108],"demonstrate":[109],"scheme":[113],"able":[115],"effectively":[117],"efficiently":[119],"lead":[120],"team":[122],"robots":[124],"cooperatively":[126],"accomplish":[127],"searching":[129],"tasks":[130]},"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":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}