{"id":"https://openalex.org/W4365800856","doi":"https://doi.org/10.1109/tro.2023.3263459","title":"Cross-Entropy Regularized Policy Gradient for Multirobot Nonadversarial Moving Target Search","display_name":"Cross-Entropy Regularized Policy Gradient for Multirobot Nonadversarial Moving Target Search","publication_year":2023,"publication_date":"2023-04-14","ids":{"openalex":"https://openalex.org/W4365800856","doi":"https://doi.org/10.1109/tro.2023.3263459"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2023.3263459","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2023.3263459","pdf_url":"https://ieeexplore.ieee.org/ielx7/8860/4359257/10102606.pdf","source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1546-1904","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/8860/4359257/10102606.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033106028","display_name":"Hongliang Guo","orcid":"https://orcid.org/0000-0002-9836-3090"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hongliang Guo","raw_affiliation_strings":["Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9836-3090","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039671584","display_name":"Zhaokai Liu","orcid":"https://orcid.org/0000-0002-7046-7998"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaokai Liu","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101454142","display_name":"Rui Shi","orcid":"https://orcid.org/0000-0002-6723-1319"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Shi","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057104857","display_name":"Wei\u2010Yun Yau","orcid":"https://orcid.org/0000-0001-5709-9169"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei-Yun Yau","raw_affiliation_strings":["Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5709-9169","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066830185","display_name":"Daniela Rus","orcid":"https://orcid.org/0000-0001-5473-3566"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniela Rus","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5473-3566","affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5094,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93096943,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"39","issue":"4","first_page":"2569","last_page":"2584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9947999715805054,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","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/T10462","display_name":"Reinforcement Learning in Robotics","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"}},{"id":"https://openalex.org/T13371","display_name":"Military Defense Systems Analysis","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6417778730392456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5675234794616699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5551198720932007},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5449735522270203},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4519188702106476},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.4185713529586792},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.355943888425827},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19567319750785828}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6417778730392456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5675234794616699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5551198720932007},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5449735522270203},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4519188702106476},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.4185713529586792},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.355943888425827},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19567319750785828},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tro.2023.3263459","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2023.3263459","pdf_url":"https://ieeexplore.ieee.org/ielx7/8860/4359257/10102606.pdf","source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1546-1904","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tro.2023.3263459","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2023.3263459","pdf_url":"https://ieeexplore.ieee.org/ielx7/8860/4359257/10102606.pdf","source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1546-1904","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1075844364","display_name":null,"funder_award_id":"C221518004","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4365800856.pdf","grobid_xml":"https://content.openalex.org/works/W4365800856.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1488353277","https://openalex.org/W2033957624","https://openalex.org/W2047599849","https://openalex.org/W2087329284","https://openalex.org/W2087421501","https://openalex.org/W2093553661","https://openalex.org/W2096145798","https://openalex.org/W2117853077","https://openalex.org/W2120465407","https://openalex.org/W2124868823","https://openalex.org/W2137766675","https://openalex.org/W2140229973","https://openalex.org/W2395575420","https://openalex.org/W2586783934","https://openalex.org/W2777506715","https://openalex.org/W2808107970","https://openalex.org/W2809931824","https://openalex.org/W2888567663","https://openalex.org/W2911191541","https://openalex.org/W2946892555","https://openalex.org/W2963888905","https://openalex.org/W2965647577","https://openalex.org/W2975968565","https://openalex.org/W2999870540","https://openalex.org/W3021513339","https://openalex.org/W3035829937","https://openalex.org/W3038238139","https://openalex.org/W3046385005","https://openalex.org/W3046763072","https://openalex.org/W3053918933","https://openalex.org/W3090023953","https://openalex.org/W3095324643","https://openalex.org/W3096656822","https://openalex.org/W3106004627","https://openalex.org/W3133150469","https://openalex.org/W3135457936","https://openalex.org/W3152521300","https://openalex.org/W3162378638","https://openalex.org/W3163926178","https://openalex.org/W3174937177","https://openalex.org/W3185416958","https://openalex.org/W3198185990","https://openalex.org/W4200635426","https://openalex.org/W4250589301","https://openalex.org/W4285792173","https://openalex.org/W4299802797","https://openalex.org/W4312252000","https://openalex.org/W6629433714","https://openalex.org/W6712181171","https://openalex.org/W6738796088","https://openalex.org/W6781719594","https://openalex.org/W6794978032","https://openalex.org/W6795908048"],"related_works":["https://openalex.org/W3008339103","https://openalex.org/W2404647514","https://openalex.org/W1667647204","https://openalex.org/W4247536566","https://openalex.org/W3119814709","https://openalex.org/W2018477250","https://openalex.org/W1508895727","https://openalex.org/W4241418540","https://openalex.org/W2725786787","https://openalex.org/W4283160672"],"abstract_inverted_index":{"This":[0],"article":[1],"investigates":[2],"the":[3,15,36,43,47,61,77,102,121,126,138,146,153,160,170,176,182,197,200,210,220],"multirobot":[4,225],"efficient":[5],"search":[6,232],"(MuRES)":[7],"for":[8,29,145],"a":[9,25,67,112,132,188,223],"nonadversarial":[10],"moving":[11,230],"target":[12,231],"problem":[13,45,155],"from":[14],"multiagent":[16,31],"reinforcement":[17,81],"learning":[18,52,55,82,122],"(MARL)":[19],"perspective.":[20],"MARL":[21,41],"is":[22,46,156],"deemed":[23],"as":[24,66,85],"promising":[26],"research":[27],"field":[28],"cooperative":[30],"applications.":[32],"However,":[33],"one":[34],"of":[35,39,79,98,209],"main":[37],"bottlenecks":[38],"applying":[40],"to":[42,119,131,180,195],"MuRES":[44],"nonstationarity":[48,154],"introduced":[49],"by":[50,186],"multiple":[51],"agents.":[53],"With":[54],"agents":[56],"simultaneously":[57],"updating":[58],"their":[59,165],"policies,":[60],"environment":[62],"cannot":[63],"be":[64],"modeled":[65],"<italic":[68,128],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[69,88,129],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">stationary</i>":[70],"Markov":[71],"decision":[72],"process,":[73],"which":[74,192],"results":[75,204],"in":[76,158,199,227],"inapplicability":[78],"fundamental":[80],"techniques":[83],"such":[84],"deep":[86],"<inline-formula":[87],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[89],"notation=\"LaTeX\">$Q$</tex-math></inline-formula>":[90],"-network":[91],"and":[92,105,109,140,205,216],"policy":[93,115,134,148],"gradient":[94,116],"(PG).":[95],"In":[96,150],"view":[97],"that,":[99],"we":[100,174,217],"adopt":[101],"centralized":[103,143,171],"training":[104,144,172],"decentralized":[106],"execution":[107],"scheme":[108],"thereby":[110],"propose":[111],"cross-entropy":[113,189],"regularized":[114],"(CE-PG)":[117],"method":[118,179],"train":[120],"agents/robots.":[123],"We":[124],"let":[125],"robots":[127,161,185,198],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">commit</i>":[130],"predetermined":[133],"during":[135,167],"execution,":[136],"collect":[137],"trajectories,":[139],"then":[141],"perform":[142],"corresponding":[147],"improvement.":[149],"this":[151],"way,":[152],"overcome,":[157],"that":[159],"do":[162],"not":[163],"update":[164],"policies":[166],"execution.":[168],"During":[169],"stage,":[173],"improve":[175],"canonical":[177],"PG":[178],"consider":[181],"interactions":[183],"among":[184],"adding":[187],"regularization":[190],"term,":[191],"essentially":[193],"functions":[194],"\u201cdisperse\u201d":[196],"environment.":[201],"Extensive":[202],"simulation":[203],"comparisons":[206],"with":[207,222],"state":[208],"art":[211],"show":[212],"CE-PG's":[213],"superior":[214],"performance,":[215],"also":[218],"validate":[219],"algorithm":[221],"real":[224],"system":[226],"an":[228],"indoor":[229],"scenario.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}