{"id":"https://openalex.org/W4416252136","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229006","title":"MARL-HE: An Improved Multi-agent Reinforcement Learning-based Pathfinding Method for Fire Evacuation Guidance","display_name":"MARL-HE: An Improved Multi-agent Reinforcement Learning-based Pathfinding Method for Fire Evacuation Guidance","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252136","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229006"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5026847323","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0001-5476-395X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ke Zhang","raw_affiliation_strings":["Waseda University,Dept. of Computer Science,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Dept. of Computer Science,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505776","display_name":"Dandan Zhu","orcid":"https://orcid.org/0009-0004-6935-1623"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dandan Zhu","raw_affiliation_strings":["China University of Petroleum,Dept. of Artificial Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"China University of Petroleum,Dept. of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101151548","display_name":"Xiaoning Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaoning Zhao","raw_affiliation_strings":["Waseda University,Dept. of Computer Science,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Dept. of Computer Science,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006799660","display_name":"S.R. Cherry","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sun Cherry","raw_affiliation_strings":["Waseda University,Dept. of Computer Science,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Dept. of Computer Science,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002145610","display_name":"Yosuke Fujisawa","orcid":"https://orcid.org/0009-0009-6576-5884"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yosuke Fujisawa","raw_affiliation_strings":["Waseda University,Dept. of Computer Science,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Dept. of Computer Science,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082205147","display_name":"Toshiharu Sugawara","orcid":"https://orcid.org/0000-0002-9271-4507"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshiharu Sugawara","raw_affiliation_strings":["Waseda University,Dept. of Computer Science,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Dept. of Computer Science,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5026847323"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45269567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.001500000013038516,"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/T11807","display_name":"Infrastructure Resilience and Vulnerability Analysis","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural 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/pathfinding","display_name":"Pathfinding","score":0.8575999736785889},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.7910000085830688},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7028999924659729},{"id":"https://openalex.org/keywords/hazard","display_name":"Hazard","score":0.4860999882221222},{"id":"https://openalex.org/keywords/shortest-path-problem","display_name":"Shortest path problem","score":0.3725999891757965},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.35519999265670776},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.3497999906539917},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.3411000072956085}],"concepts":[{"id":"https://openalex.org/C25321074","wikidata":"https://www.wikidata.org/wiki/Q1969601","display_name":"Pathfinding","level":4,"score":0.8575999736785889},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.7910000085830688},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7028999924659729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6571000218391418},{"id":"https://openalex.org/C49261128","wikidata":"https://www.wikidata.org/wiki/Q1132455","display_name":"Hazard","level":2,"score":0.4860999882221222},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.3725999891757965},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.367000013589859},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.3497999906539917},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C201004817","wikidata":"https://www.wikidata.org/wiki/Q1707071","display_name":"Guidance system","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.30250000953674316},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2948000133037567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2896000146865845},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3026322993","https://openalex.org/W3032851638","https://openalex.org/W4402817918"],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,53,58,64,78,86,92,151],"multi-agent":[2,108,136,188],"pathfinding":[3,74,112],"problem,":[4],"an":[5,30,127,145],"agent":[6,168],"may":[7],"have":[8],"multiple":[9,43],"possible":[10],"destinations,":[11],"each":[12,167],"of":[13,21,60,80,88,94,173],"which":[14,117,164],"must":[15],"be":[16,246],"appropriately":[17],"selected":[18],"in":[19,29,39],"terms":[20],"conflict":[22],"avoidance":[23],"and":[24,63,84,91,134,214,227,236,243],"shortest":[25,54],"path.":[26],"For":[27],"example,":[28],"evacuation":[31,73,115,190,211,218,229,238],"system":[32,192],"when":[33],"faced":[34],"with":[35,42,123],"a":[36,40,107,187,194,208,225],"fire":[37,65,189,196],"hazard":[38,114,156,197],"building":[41],"exits":[44],"for":[45,111],"evacuation,":[46],"agents":[47,62,83,90,166],"need":[48],"to":[49,67,99,149,170,177,232],"consider":[50,77],"not":[51],"only":[52,76],"path":[55,231],"but":[56],"also":[57],"conflicts":[59],"other":[61,89,165],"spread":[66,93],"respond":[68],"appropriately.":[69],"However,":[70],"recent":[71],"reinforcement-learning-based":[72],"methods":[75],"scenarios":[79],"independent":[81],"individual":[82,234],"ignore":[85],"influence":[87],"fire,":[95],"limiting":[96],"their":[97,174],"application":[98],"evacuation.":[100,157],"To":[101,181],"address":[102],"these":[103],"issues,":[104],"we":[105,185],"propose":[106],"reinforcement":[109,121],"learning":[110,122],"during":[113,155],"(MARL-HE),":[116],"is":[118],"integrated":[119],"into":[120],"two":[124],"novel":[125],"components:":[126],"efficient":[128],"artificial":[129,146],"potential":[130,147],"field":[131,148],"adapter":[132,143],"(APF-adapter)":[133],"policy-sharing-enhanced":[135],"proximity":[137],"policy":[138,160,175],"optimization":[139],"(PS-MAPPO).":[140],"The":[141,199,240],"APF":[142],"utilizes":[144],"eliminate":[150],"dynamic":[152],"state":[153],"transitions":[154],"PS-MAPPO":[158],"leverages":[159],"sharing":[161],"by":[162],"determining":[163],"has":[169],"share":[171],"part":[172],"model":[176],"accelerate":[178],"training":[179],"efficiency.":[180,239],"evaluate":[182],"our":[183,204],"method,":[184],"built":[186],"guidance":[191,230],"(MAFEGS),":[193],"Unity-based":[195],"environment.":[198],"experimental":[200],"results":[201],"show":[202],"that":[203],"MARL-HE":[205],"method":[206],"achieved":[207],"7.02%":[209],"higher":[210],"success":[212],"rate":[213],"25.12%":[215],"lower":[216],"average":[217],"number":[219],"than":[220],"MAPPO.":[221],"MAFEGS":[222],"can":[223,245],"plan":[224],"safer":[226],"faster":[228],"keep":[233],"safe":[235],"increase":[237],"simulation":[241],"environment":[242],"code":[244],"downloaded":[247],"from:":[248],"https://github.com/ColaZhang22/PS_MARL_PF.":[249]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}