{"id":"https://openalex.org/W4389666982","doi":"https://doi.org/10.1109/iros55552.2023.10342261","title":"HELSA: Hierarchical Reinforcement Learning with Spatiotemporal Abstraction for Large-Scale Multi-Agent Path Finding","display_name":"HELSA: Hierarchical Reinforcement Learning with Spatiotemporal Abstraction for Large-Scale Multi-Agent Path Finding","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389666982","doi":"https://doi.org/10.1109/iros55552.2023.10342261"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5101796496","display_name":"Zhaoyi Song","orcid":"https://orcid.org/0009-0002-7888-8700"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaoyi Song","raw_affiliation_strings":["School of Software Engineering, Tongji University,Shanghai,China,200092"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Tongji University,Shanghai,China,200092","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695813","display_name":"Rongqing Zhang","orcid":"https://orcid.org/0000-0003-3774-6247"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongqing Zhang","raw_affiliation_strings":["School of Software Engineering, Tongji University,Shanghai,China,200092"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Tongji University,Shanghai,China,200092","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068110218","display_name":"Xiang Cheng","orcid":"https://orcid.org/0000-0002-5943-0326"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Cheng","raw_affiliation_strings":["School of Electronics, Peking University,Beijing,China,100871"],"affiliations":[{"raw_affiliation_string":"School of Electronics, Peking University,Beijing,China,100871","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101796496"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.8597,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76281363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7318","last_page":"7325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9936000108718872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8507055044174194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7459003329277039},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6828114986419678},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.5915923714637756},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5040878057479858},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4890500009059906},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.47955676913261414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47158753871917725},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46828147768974304},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.43004193902015686},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4202800691127777},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33857521414756775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10959357023239136}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8507055044174194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459003329277039},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6828114986419678},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.5915923714637756},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5040878057479858},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4890500009059906},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.47955676913261414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47158753871917725},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46828147768974304},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.43004193902015686},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4202800691127777},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33857521414756775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10959357023239136},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2014663916","display_name":null,"funder_award_id":"2021ZD0112700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G606678594","display_name":null,"funder_award_id":"62271351,62125101,62341101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1549280300","https://openalex.org/W2109910161","https://openalex.org/W2191404279","https://openalex.org/W2406007181","https://openalex.org/W2892258706","https://openalex.org/W2913756371","https://openalex.org/W2964997335","https://openalex.org/W2998367975","https://openalex.org/W3092786062","https://openalex.org/W3103635569","https://openalex.org/W3129616587","https://openalex.org/W3133734443","https://openalex.org/W3166401044","https://openalex.org/W3201099806","https://openalex.org/W3206082228","https://openalex.org/W6620707391","https://openalex.org/W6632662516","https://openalex.org/W6697106730","https://openalex.org/W6748554570"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W1914583973","https://openalex.org/W2130711276","https://openalex.org/W4308828368"],"abstract_inverted_index":{"The":[0],"Multi-Agent":[1],"Path":[2],"Finding":[3],"(MAPF)":[4],"problem":[5],"is":[6,23],"a":[7,24,32,48,57,86,108],"critical":[8],"challenge":[9],"in":[10,31,144],"dynamic":[11],"multi-robot":[12,42],"systems.":[13],"Recent":[14],"studies":[15],"have":[16],"revealed":[17],"that":[18,89,111,138],"multi-agent":[19,65],"reinforcement":[20,59],"learning":[21,60],"(MARL)":[22],"promising":[25],"approach":[26],"to":[27,51,74],"solving":[28],"MAPF":[29],"problems":[30],"fully":[33],"decentralized":[34],"manner.":[35],"However,":[36],"as":[37],"the":[38,41,91],"size":[39],"of":[40,134,146],"system":[43],"increases,":[44],"sample":[45],"inefficiency":[46],"becomes":[47],"major":[49],"impediment":[50],"learning-based":[52],"methods.":[53],"This":[54],"paper":[55],"presents":[56],"hierarchical":[58],"(HRL)":[61],"framework":[62],"for":[63],"large-scale":[64],"path":[66],"finding,":[67],"featuring":[68],"applying":[69],"spatial":[70],"and":[71,78,96,120,150],"temporal":[72],"abstraction":[73],"capture":[75],"intermediate":[76],"reward":[77],"thus":[79],"encourage":[80],"efficient":[81],"exploration.":[82],"Specifically,":[83],"we":[84,106],"introduce":[85],"meta":[87],"controller":[88,110],"partitions":[90],"map":[92],"into":[93],"interconnected":[94],"regions":[95],"optimizes":[97],"agents'":[98],"region-wise":[99],"paths":[100],"towards":[101],"globally":[102],"better":[103],"solutions.":[104],"Additionally,":[105],"design":[107],"lower-level":[109],"efficiently":[112],"solves":[113],"each":[114],"sub-problem":[115],"by":[116],"incorporating":[117],"heuristic":[118],"guidance":[119],"an":[121],"inter-agent":[122],"communication":[123],"mechanism":[124],"with":[125],"RL-based":[126],"policies.":[127],"Our":[128],"empirical":[129],"results":[130],"on":[131],"test":[132],"instances":[133],"various":[135],"scales":[136],"demonstrate":[137],"our":[139],"method":[140],"outperforms":[141],"existing":[142],"approaches":[143],"terms":[145],"both":[147],"success":[148],"rate":[149],"makespan.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}