{"id":"https://openalex.org/W4386322136","doi":"https://doi.org/10.1109/tnnls.2023.3303502","title":"When to Switch: Planning and Learning for Partially Observable Multi-Agent Pathfinding","display_name":"When to Switch: Planning and Learning for Partially Observable Multi-Agent Pathfinding","publication_year":2023,"publication_date":"2023-08-31","ids":{"openalex":"https://openalex.org/W4386322136","doi":"https://doi.org/10.1109/tnnls.2023.3303502","pmid":"https://pubmed.ncbi.nlm.nih.gov/37651484"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3303502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3303502","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5089256022","display_name":"Alexey Skrynnik","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alexey Skrynnik","raw_affiliation_strings":["Federal Research Center for Computer Science and Control of Russian Academy of Science, Moscow, Russia","AIRI, Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Federal Research Center for Computer Science and Control of Russian Academy of Science, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"AIRI, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020304186","display_name":"Anton Andreychuk","orcid":"https://orcid.org/0000-0001-5320-4603"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anton Andreychuk","raw_affiliation_strings":["AIRI, Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"AIRI, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056981356","display_name":"Konstantin Yakovlev","orcid":"https://orcid.org/0000-0002-4377-321X"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Konstantin Yakovlev","raw_affiliation_strings":["Federal Research Center for Computer Science and Control of Russian Academy of Science, Moscow, Russia","AIRI, Moscow, Russia","Faculty of Computer Science, HSE University, Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Federal Research Center for Computer Science and Control of Russian Academy of Science, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"AIRI, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"Faculty of Computer Science, HSE University, Moscow, Russia","institution_ids":["https://openalex.org/I118501908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080806360","display_name":"Aleksandr I. Panov","orcid":"https://orcid.org/0000-0002-9747-3837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksandr I. Panov","raw_affiliation_strings":["Federal Research Center for Computer Science and Control of Russian Academy of Science, Moscow, Russia","AIRI, Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Federal Research Center for Computer Science and Control of Russian Academy of Science, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"AIRI, Moscow, Russia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089256022"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9258,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88302908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"35","issue":"12","first_page":"17411","last_page":"17424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9991999864578247,"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":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9932000041007996,"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":0.9883000254631042,"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/pathfinding","display_name":"Pathfinding","score":0.8743520975112915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7554478049278259},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.7138383388519287},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.692672848701477},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.652105987071991},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6441634297370911},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6147152185440063},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4951075613498688},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4581739902496338},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4562600255012512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45262759923934937},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4327560067176819},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4039934277534485},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15609875321388245},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07565069198608398}],"concepts":[{"id":"https://openalex.org/C25321074","wikidata":"https://www.wikidata.org/wiki/Q1969601","display_name":"Pathfinding","level":4,"score":0.8743520975112915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554478049278259},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.7138383388519287},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.692672848701477},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.652105987071991},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6441634297370911},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6147152185440063},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4951075613498688},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4581739902496338},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4562600255012512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45262759923934937},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4327560067176819},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4039934277534485},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15609875321388245},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07565069198608398},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3303502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3303502","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37651484","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37651484","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W192919555","https://openalex.org/W1551562380","https://openalex.org/W1969483458","https://openalex.org/W1986164452","https://openalex.org/W1989407213","https://openalex.org/W2046431055","https://openalex.org/W2100695938","https://openalex.org/W2124015815","https://openalex.org/W2155313135","https://openalex.org/W2166462345","https://openalex.org/W2168359464","https://openalex.org/W2241553860","https://openalex.org/W2292985786","https://openalex.org/W2573311857","https://openalex.org/W2605824764","https://openalex.org/W2736601468","https://openalex.org/W2791846357","https://openalex.org/W2808589448","https://openalex.org/W2892258706","https://openalex.org/W2903837854","https://openalex.org/W2904325460","https://openalex.org/W2914296650","https://openalex.org/W2963864421","https://openalex.org/W2964997335","https://openalex.org/W2965850033","https://openalex.org/W2981057983","https://openalex.org/W2987132678","https://openalex.org/W2996037775","https://openalex.org/W3011643348","https://openalex.org/W3025769768","https://openalex.org/W3084487819","https://openalex.org/W3088197938","https://openalex.org/W3092786062","https://openalex.org/W3095041969","https://openalex.org/W3099318416","https://openalex.org/W3103572865","https://openalex.org/W3103635569","https://openalex.org/W3129616587","https://openalex.org/W3133734443","https://openalex.org/W3206082228","https://openalex.org/W3210169707","https://openalex.org/W4212814156","https://openalex.org/W4221155367","https://openalex.org/W4286748781","https://openalex.org/W4292236478","https://openalex.org/W4313484354","https://openalex.org/W4319165238","https://openalex.org/W4366238939","https://openalex.org/W4394662461","https://openalex.org/W6675090247","https://openalex.org/W6684921986","https://openalex.org/W6696955428","https://openalex.org/W6738126737","https://openalex.org/W6738741286","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6749304979","https://openalex.org/W6752419568","https://openalex.org/W6758846586","https://openalex.org/W6771750343","https://openalex.org/W6772005887","https://openalex.org/W6780153092","https://openalex.org/W6792346553","https://openalex.org/W6795908048","https://openalex.org/W6863618527"],"related_works":["https://openalex.org/W4285687848","https://openalex.org/W4289994039","https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W2240526870","https://openalex.org/W3100156731","https://openalex.org/W2623016776","https://openalex.org/W4312814274","https://openalex.org/W1590307681"],"abstract_inverted_index":{"Multi-agent":[0],"pathfinding":[1],"(MAPF)":[2],"is":[3,34,77,91,125,169,192],"a":[4,9,15,21,28,52,80,121,156],"problem":[5,179],"that":[6,58,82,124,161],"involves":[7],"finding":[8],"set":[10,16],"of":[11,17,150,158],"non-conflicting":[12],"paths":[13],"for":[14,38,99],"agents":[18,49,60],"confined":[19],"to":[20,78,87,171,174],"graph.":[22],"In":[23],"this":[24],"work,":[25],"we":[26,56,94,119],"study":[27],"MAPF":[29,103],"setting,":[30],"where":[31],"the":[32,45,59,84,130,138,140,143,152,162,166,175,184],"environment":[33],"only":[35,50],"partially":[36,101],"observable":[37,102],"each":[39],"agent,":[40],"i.e.,":[41],"an":[42],"agent":[43],"observes":[44],"obstacles":[46],"and":[47,64,110,142,178,188],"other":[48],"within":[51],"limited":[53],"field-of-view.":[54],"Moreover,":[55],"assume":[57],"do":[61,65],"not":[62,66],"communicate":[63],"share":[67],"knowledge":[68],"on":[69,107,114,127],"their":[70],"goals,":[71],"intended":[72],"actions,":[73],"etc.":[74],"The":[75,190],"task":[76],"construct":[79],"policy":[81,123,164],"maps":[83,177],"agent's":[85],"observations":[86],"actions.":[88],"Our":[89],"contribution":[90],"multifold.":[92],"First,":[93],"propose":[95],"two":[96],"novel":[97],"policies":[98,154],"solving":[100],"(PO-MAPF):":[104],"one":[105,112],"based":[106,113,126],"heuristic":[108],"search":[109],"another":[111],"reinforcement":[115],"learning":[116],"(RL).":[117],"Next,":[118],"introduce":[120],"mixed":[122],"switching":[128],"between":[129],"two.":[131],"We":[132],"suggest":[133],"three":[134],"different":[135],"switch":[136],"scenarios:":[137],"heuristic,":[139],"deterministic,":[141],"learnable":[144],"one.":[145],"A":[146],"thorough":[147],"empirical":[148],"evaluation":[149],"all":[151],"proposed":[153],"in":[155],"variety":[157],"setups":[159],"shows":[160],"mixing":[163],"demonstrates":[165],"best":[167],"performance":[168],"able":[170],"generalize":[172],"well":[173],"unseen":[176],"instances,":[180],"and,":[181],"additionally,":[182],"outperforms":[183],"state-of-the-art":[185],"counterparts":[186],"(PRIMAL2":[187],"PICO).":[189],"source-code":[191],"available":[193],"at":[194],"https://github.com/AIRI-Institute/when-to-switch.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}