{"id":"https://openalex.org/W7131862110","doi":"https://doi.org/10.1115/1.4071239","title":"Efficient Training in Multiagent Reinforcement Learning: A Communication-Free Framework for the Box-Pushing Problem","display_name":"Efficient Training in Multiagent Reinforcement Learning: A Communication-Free Framework for the Box-Pushing Problem","publication_year":2026,"publication_date":"2026-02-27","ids":{"openalex":"https://openalex.org/W7131862110","doi":"https://doi.org/10.1115/1.4071239"},"language":"en","primary_location":{"id":"doi:10.1115/1.4071239","is_oa":true,"landing_page_url":"https://doi.org/10.1115/1.4071239","pdf_url":"https://asmedigitalcollection.asme.org/computingengineering/article-pdf/doi/10.1115/1.4071239/7597022/jcise-25-1538.pdf","source":{"id":"https://openalex.org/S173178594","display_name":"Journal of Computing and Information Science in Engineering","issn_l":"1530-9827","issn":["1530-9827","1944-7078"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316053","host_organization_name":"ASM International","host_organization_lineage":["https://openalex.org/P4310316053"],"host_organization_lineage_names":["ASM International"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computing and Information Science in Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://asmedigitalcollection.asme.org/computingengineering/article-pdf/doi/10.1115/1.4071239/7597022/jcise-25-1538.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127182979","display_name":"David Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Ge","raw_affiliation_strings":["Columbia University Department of Computer Science, , New York, NY 10027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University Department of Computer Science, , New York, NY 10027","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127472402","display_name":"Hao Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Ji","raw_affiliation_strings":["University of Southern California Center for Advanced Research Computing, , Los Angeles, CA 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California Center for Advanced Research Computing, , Los Angeles, CA 90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127079173","display_name":"Tsung-Jui Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsung-Jui Wu","raw_affiliation_strings":["University of Southern California Department of Computer Science, , Los Angeles, CA 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California Department of Computer Science, , Los Angeles, CA 90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106279489","display_name":"Bingling Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I142934699","display_name":"California State University, Fullerton","ror":"https://ror.org/02avqqw26","country_code":"US","type":"education","lineage":["https://openalex.org/I142934699"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bingling Huang","raw_affiliation_strings":["California State University, Fullerton Department of Mechanical Engineering, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California State University, Fullerton Department of Mechanical Engineering, ,","institution_ids":["https://openalex.org/I142934699"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127210938","display_name":"Quanchao Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quanchao Lu","raw_affiliation_strings":["Georgia Institute of Technology School of Computer Science, , Atlanta, GA 30332"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology School of Computer Science, , Atlanta, GA 30332","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127104471","display_name":"Shuo Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo Shi","raw_affiliation_strings":["Brandeis University Michtom School of Computer Science, , Waltham, MA 02453"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brandeis University Michtom School of Computer Science, , Waltham, MA 02453","institution_ids":["https://openalex.org/I6902469"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19784888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7664999961853027,"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":0.7664999961853027,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.01510000042617321,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.014700000174343586,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7940000295639038},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6373000144958496},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6212000250816345},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6039000153541565},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4587000012397766},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4496000111103058},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.36469998955726624}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7940000295639038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218999862670898},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6373000144958496},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6212000250816345},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6039000153541565},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4733000099658966},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3743000030517578},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3174000084400177},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1115/1.4071239","is_oa":true,"landing_page_url":"https://doi.org/10.1115/1.4071239","pdf_url":"https://asmedigitalcollection.asme.org/computingengineering/article-pdf/doi/10.1115/1.4071239/7597022/jcise-25-1538.pdf","source":{"id":"https://openalex.org/S173178594","display_name":"Journal of Computing and Information Science in Engineering","issn_l":"1530-9827","issn":["1530-9827","1944-7078"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316053","host_organization_name":"ASM International","host_organization_lineage":["https://openalex.org/P4310316053"],"host_organization_lineage_names":["ASM International"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computing and Information Science in Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1115/1.4071239","is_oa":true,"landing_page_url":"https://doi.org/10.1115/1.4071239","pdf_url":"https://asmedigitalcollection.asme.org/computingengineering/article-pdf/doi/10.1115/1.4071239/7597022/jcise-25-1538.pdf","source":{"id":"https://openalex.org/S173178594","display_name":"Journal of Computing and Information Science in Engineering","issn_l":"1530-9827","issn":["1530-9827","1944-7078"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316053","host_organization_name":"ASM International","host_organization_lineage":["https://openalex.org/P4310316053"],"host_organization_lineage_names":["ASM International"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computing and Information Science in Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.691718578338623,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7131862110.pdf","grobid_xml":"https://content.openalex.org/works/W7131862110.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Effective":[1],"coordination":[2],"is":[3,89,95,148,202],"a":[4,96,111,156,164,167,193],"critical":[5],"challenge":[6,39],"in":[7,15,44,55,91,152],"the":[8,51,70,83,137,153],"design":[9],"of":[10,86,146],"self-organizing":[11],"systems":[12],"(SOSs),":[13],"particularly":[14],"decentralized":[16],"training":[17,52],"where":[18,50,200],"explicit":[19],"communication":[20,201],"incurs":[21],"high":[22,138],"costs.":[23],"Traditional":[24],"approaches":[25],"often":[26],"rely":[27],"on":[28,75],"inter-agent":[29],"communication,":[30,77],"but":[31],"this":[32,62,92],"can":[33],"introduce":[34],"substantial":[35],"system":[36],"overhead.":[37],"The":[38,144],"becomes":[40],"even":[41],"more":[42,124],"pronounced":[43],"multiagent":[45],"reinforcement":[46],"learning":[47],"(MARL)-based":[48],"systems,":[49],"process":[53],"happens":[54],"an":[56],"end-to-end":[57],"black-box":[58],"manner.":[59],"To":[60],"address":[61],"issue,":[63],"we":[64],"explore":[65],"alternative":[66],"methods":[67],"to":[68,100,131,161],"enhance":[69],"exploration":[71],"phase":[72],"without":[73,135],"relying":[74],"direct":[76],"thereby":[78],"improving":[79],"search":[80],"efficiency.":[81],"Therefore,":[82],"shared":[84,105],"pool":[85],"information":[87,106],"(SPI)":[88],"proposed":[90],"article,":[93],"which":[94],"communication-free":[97],"framework":[98],"designed":[99],"provide":[101],"agents":[102,130,160],"with":[103,141],"structured":[104],"at":[107],"initialization.":[108],"By":[109],"offering":[110],"common":[112],"foundation":[113],"for":[114,198],"exploration,":[115],"SPI":[116,147,176,191],"helps":[117],"guide":[118],"group":[119],"action":[120],"choices":[121],"and":[122,150,184,195],"facilitates":[123],"effective":[125],"decision-making.":[126],"This":[127],"approach":[128,197],"enables":[129],"learn":[132],"coordinated":[133],"behaviors":[134],"bringing":[136],"costs":[139],"associated":[140],"continuous":[142],"communication.":[143],"efficiency":[145],"assessed":[149],"validated":[151],"box-pushing":[154],"problem,":[155],"task":[157],"that":[158,175],"requires":[159],"collaboratively":[162],"maneuver":[163],"box":[165],"toward":[166],"goal":[168],"while":[169],"avoiding":[170],"obstacles.":[171],"Our":[172],"findings":[173],"indicate":[174],"accelerates":[177],"learning,":[178],"enhances":[179],"coordination,":[180],"increases":[181],"success":[182],"rates,":[183],"optimizes":[185],"trajectory":[186],"optimization.":[187],"These":[188],"results":[189],"highlight":[190],"as":[192],"promising":[194],"scalable":[196],"scenarios":[199],"costly":[203],"or":[204],"infeasible.":[205]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-28T00:00:00"}