{"id":"https://openalex.org/W7161141847","doi":"https://doi.org/10.1016/j.robot.2026.105530","title":"MA2MB: Multi-agent mutual-advising model-based reinforcement learning for pursuit and evasion games","display_name":"MA2MB: Multi-agent mutual-advising model-based reinforcement learning for pursuit and evasion games","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161141847","doi":"https://doi.org/10.1016/j.robot.2026.105530"},"language":"en","primary_location":{"id":"doi:10.1016/j.robot.2026.105530","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.robot.2026.105530","pdf_url":null,"source":{"id":"https://openalex.org/S133768115","display_name":"Robotics and Autonomous Systems","issn_l":"0921-8890","issn":["0921-8890","1872-793X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Autonomous Systems","raw_type":"journal-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/A5136099178","display_name":"Baolin Zhao","orcid":"https://orcid.org/0009-0009-6529-4015"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baolin Zhao","raw_affiliation_strings":["College of Computer Science and Technology, Ocean University of China, Qingdao, 266404, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0009-6529-4015","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Ocean University of China, Qingdao, 266404, Shandong, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127983003","display_name":"Qi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Guo","raw_affiliation_strings":["College of Computer Science and Technology, Ocean University of China, Qingdao, 266404, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Ocean University of China, Qingdao, 266404, Shandong, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015622958","display_name":"X Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiandong Wang","raw_affiliation_strings":["College of Computer Science and Technology, Ocean University of China, Qingdao, 266404, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Ocean University of China, Qingdao, 266404, Shandong, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136104751","display_name":"Rachid Hedjam","orcid":null},"institutions":[{"id":"https://openalex.org/I113281461","display_name":"Bishop's University","ror":"https://ror.org/051prj435","country_code":"CA","type":"education","lineage":["https://openalex.org/I113281461"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rachid Hedjam","raw_affiliation_strings":["Department of Computer Science, Bishop\u2019s University, Sherbrooke, J1M 1Z7, Quebec, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Bishop\u2019s University, Sherbrooke, J1M 1Z7, Quebec, Canada","institution_ids":["https://openalex.org/I113281461"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136130237","display_name":"Guoqiang Zhong","orcid":"https://orcid.org/0000-0002-2952-6642"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guoqiang Zhong","raw_affiliation_strings":["College of Computer Science and Technology, Ocean University of China, Qingdao, 266404, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0002-2952-6642","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Ocean University of China, Qingdao, 266404, Shandong, China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5136130237"],"corresponding_institution_ids":["https://openalex.org/I59028903"],"apc_list":{"value":3020,"currency":"USD","value_usd":3020},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87562808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"203","issue":null,"first_page":"105530","last_page":"105530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9817000031471252,"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"}},"topics":[{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.9817000031471252,"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"}},{"id":"https://openalex.org/T13371","display_name":"Military Defense Systems Analysis","score":0.004900000058114529,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.002300000051036477,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8508999943733215},{"id":"https://openalex.org/keywords/pursuer","display_name":"Pursuer","score":0.843999981880188},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7484999895095825},{"id":"https://openalex.org/keywords/evasion","display_name":"Evasion (ethics)","score":0.613099992275238},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6098999977111816},{"id":"https://openalex.org/keywords/pursuit-evasion","display_name":"Pursuit-evasion","score":0.5338000059127808},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.5139999985694885},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.5095999836921692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8636000156402588},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8508999943733215},{"id":"https://openalex.org/C2776927521","wikidata":"https://www.wikidata.org/wiki/Q468489","display_name":"Pursuer","level":2,"score":0.843999981880188},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7484999895095825},{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.613099992275238},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6098999977111816},{"id":"https://openalex.org/C2778388243","wikidata":"https://www.wikidata.org/wiki/Q7261573","display_name":"Pursuit-evasion","level":2,"score":0.5338000059127808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.53329998254776},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.5139999985694885},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3763999938964844},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25429999828338623},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.robot.2026.105530","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.robot.2026.105530","pdf_url":null,"source":{"id":"https://openalex.org/S133768115","display_name":"Robotics and Autonomous Systems","issn_l":"0921-8890","issn":["0921-8890","1872-793X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Autonomous Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4694056808948517,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322866","display_name":"Natural Science Foundation of Hainan Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2954093458","https://openalex.org/W3000179003","https://openalex.org/W3122447121","https://openalex.org/W3185539947","https://openalex.org/W3205953818","https://openalex.org/W4212793312","https://openalex.org/W4213246061","https://openalex.org/W4226329847","https://openalex.org/W4285225935","https://openalex.org/W4304480072","https://openalex.org/W4315489393","https://openalex.org/W4380303677","https://openalex.org/W4385656622","https://openalex.org/W4385767399","https://openalex.org/W4385767524","https://openalex.org/W4387245268","https://openalex.org/W4387415195","https://openalex.org/W4388740239","https://openalex.org/W4388966807","https://openalex.org/W4391019876","https://openalex.org/W4391147933","https://openalex.org/W4394682729","https://openalex.org/W4394744264","https://openalex.org/W4403674850","https://openalex.org/W4405394947","https://openalex.org/W4409919758","https://openalex.org/W4414573788","https://openalex.org/W4415000746","https://openalex.org/W7124267618","https://openalex.org/W7124298089"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2026-05-15T00:00:00"}
