{"id":"https://openalex.org/W4383112356","doi":"https://doi.org/10.1109/lra.2023.3292004","title":"SACHA: Soft Actor-Critic With Heuristic-Based Attention for Partially Observable Multi-Agent Path Finding","display_name":"SACHA: Soft Actor-Critic With Heuristic-Based Attention for Partially Observable Multi-Agent Path Finding","publication_year":2023,"publication_date":"2023-07-04","ids":{"openalex":"https://openalex.org/W4383112356","doi":"https://doi.org/10.1109/lra.2023.3292004"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3292004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3292004","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2307.02691","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101410782","display_name":"Qiushi Lin","orcid":"https://orcid.org/0009-0008-3964-1426"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Qiushi Lin","raw_affiliation_strings":["School of Computing Science, Simon Fraser University, Burnaby, BC, Canada"],"raw_orcid":"https://orcid.org/0009-0008-3964-1426","affiliations":[{"raw_affiliation_string":"School of Computing Science, Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024389928","display_name":"Hang Ma","orcid":"https://orcid.org/0000-0002-0602-0999"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hang Ma","raw_affiliation_strings":["School of Computing Science, Simon Fraser University, Burnaby, BC, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0602-0999","affiliations":[{"raw_affiliation_string":"School of Computing Science, Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6896,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.97495461,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"8","issue":"8","first_page":"5100","last_page":"5107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.8066386580467224},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.725059449672699},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5950649380683899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4560007154941559},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4362490773200989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3350945711135864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2930246591567993},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0913558304309845}],"concepts":[{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.8066386580467224},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.725059449672699},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5950649380683899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4560007154941559},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4362490773200989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3350945711135864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2930246591567993},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0913558304309845},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2023.3292004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3292004","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2307.02691","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.02691","pdf_url":"https://arxiv.org/pdf/2307.02691","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.02691","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.02691","pdf_url":"https://arxiv.org/pdf/2307.02691","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G8111255295","display_name":null,"funder_award_id":"RGPIN2020-06540","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4383112356.pdf"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1549280300","https://openalex.org/W1641379095","https://openalex.org/W1989407213","https://openalex.org/W2081631327","https://openalex.org/W2123030512","https://openalex.org/W2124015815","https://openalex.org/W2155027007","https://openalex.org/W2191404279","https://openalex.org/W2268708260","https://openalex.org/W2296073425","https://openalex.org/W2577436009","https://openalex.org/W2617547828","https://openalex.org/W2627004156","https://openalex.org/W2768629321","https://openalex.org/W2781726626","https://openalex.org/W2892258706","https://openalex.org/W2894976951","https://openalex.org/W2903998385","https://openalex.org/W2949992533","https://openalex.org/W2963658727","https://openalex.org/W2963864421","https://openalex.org/W2964015378","https://openalex.org/W2964043796","https://openalex.org/W2964997335","https://openalex.org/W2968526727","https://openalex.org/W3037164939","https://openalex.org/W3103635569","https://openalex.org/W3129616587","https://openalex.org/W3143404981","https://openalex.org/W3172461472","https://openalex.org/W3201099806","https://openalex.org/W3206082228","https://openalex.org/W4287115669","https://openalex.org/W4299802797","https://openalex.org/W4302760542","https://openalex.org/W4385245566","https://openalex.org/W6632662516","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6693839119","https://openalex.org/W6726873649","https://openalex.org/W6732454287","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6747473740","https://openalex.org/W6755069753","https://openalex.org/W6767091432","https://openalex.org/W6797434948"],"related_works":["https://openalex.org/W1994680671","https://openalex.org/W2000283393","https://openalex.org/W2002320543","https://openalex.org/W2061947244","https://openalex.org/W2150232912","https://openalex.org/W2054940838","https://openalex.org/W3106170641","https://openalex.org/W4321855183","https://openalex.org/W2952513607","https://openalex.org/W3102440103"],"abstract_inverted_index":{"Multi-Agent":[0],"Path":[1],"Finding":[2],"(MAPF)":[3],"is":[4],"a":[5,42,47,84,114,156,176,216,237],"crucial":[6],"component":[7],"for":[8,101,117,140],"many":[9],"large-scale":[10],"robotic":[11],"systems,":[12],"where":[13],"agents":[14,132,205],"must":[15],"plan":[16],"their":[17,21],"collision-free":[18],"paths":[19],"to":[20,32,72,107,120,124,163,171,198,224,254],"given":[22],"goal":[23],"positions.":[24],"Recently,":[25],"multi-agent":[26,65,85,151,182],"reinforcement":[27],"learning":[28,41,143],"has":[29],"been":[30],"introduced":[31],"solve":[33],"the":[34,73,103,125,149,195,220],"partially":[35],"observable":[36,178],"variant":[37],"of":[38,75,136,144,194,204,208,239],"MAPF":[39,199,240,250],"by":[40,154],"decentralized":[43],"single-agent":[44],"policy":[45,197,222],"in":[46,62,68,186,219],"centralized":[48],"fashion":[49],"based":[50],"on":[51,160,236],"each":[52,118,161],"agent's":[53,221],"partial":[54],"observation.":[55],"However,":[56],"existing":[57,150,172],"learning-based":[58,249],"methods":[59,173,251],"are":[60],"ineffective":[61],"achieving":[63],"complex":[64],"cooperation,":[66],"especially":[67],"congested":[69],"environments,":[70],"due":[71],"non-stationarity":[74],"this":[76,80],"setting.":[77],"To":[78],"tackle":[79],"challenge,":[81],"we":[82],"propose":[83],"actor-critic":[86,152,183],"method":[87,184],"called":[88],"Soft":[89],"Actor-Critic":[90],"with":[91,201,252],"Heuristic-Based":[92],"Attention":[93],"(SACHA),":[94],"which":[95,214],"employs":[96],"novel":[97,157],"heuristic-based":[98],"attention":[99,123],"mechanisms":[100],"both":[102,232],"actors":[104],"and":[105,191,206,234,242,257],"critics":[106],"encourage":[108],"cooperation":[109],"among":[110,228],"agents.":[111,229],"SACHA":[112,146,233],"learns":[113],"neural":[115],"network":[116,223],"agent":[119,162],"selectively":[121],"pay":[122],"shortest":[126],"path":[127],"heuristic":[128],"guidance":[129],"from":[130],"multiple":[131],"within":[133],"its":[134],"field":[135],"view,":[137],"thereby":[138],"allowing":[139],"more":[141,187],"scalable":[142],"cooperation.":[145],"also":[147,211],"extends":[148],"framework":[153],"introducing":[155],"critic":[158],"centered":[159],"approximate":[164],"<inline-formula":[165],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[167],"notation=\"LaTeX\">$Q$</tex-math></inline-formula>":[168],"-values.":[169],"Compared":[170],"that":[174],"use":[175],"fully":[177],"critic,":[179],"our":[180],"agent-centered":[181],"results":[185],"impartial":[188],"credit":[189],"assignment":[190],"better":[192],"generalizability":[193],"learned":[196],"instances":[200,241],"varying":[202],"numbers":[203],"types":[207],"environments.":[209],"We":[210,230],"implement":[212],"SACHA(C),":[213],"embeds":[215],"communication":[217],"module":[218],"enable":[225],"information":[226],"exchange":[227],"evaluate":[231],"SACHA(C)":[235],"variety":[238],"demonstrate":[243],"decent":[244],"improvements":[245],"over":[246],"several":[247],"state-of-the-art":[248],"respect":[253],"success":[255],"rate":[256],"solution":[258],"quality.":[259]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}