{"id":"https://openalex.org/W4389667356","doi":"https://doi.org/10.1109/iros55552.2023.10341563","title":"Decentralized Multi-Agent Reinforcement Learning with Global State Prediction","display_name":"Decentralized Multi-Agent Reinforcement Learning with Global State Prediction","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667356","doi":"https://doi.org/10.1109/iros55552.2023.10341563"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341563","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":"conference-paper","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/A5068837797","display_name":"J. S. Bloom","orcid":"https://orcid.org/0000-0002-7777-216X"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Bloom","raw_affiliation_strings":["Worcester Polytechnic Institute,Robotics Engineering,Worcester,MA,USA","Robotics Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute,Robotics Engineering,Worcester,MA,USA","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Robotics Engineering, Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025264192","display_name":"Pranjal Paliwal","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pranjal Paliwal","raw_affiliation_strings":["Worcester Polytechnic Institute,Robotics Engineering,Worcester,MA,USA","Robotics Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute,Robotics Engineering,Worcester,MA,USA","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Robotics Engineering, Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031205037","display_name":"Apratim Mukherjee","orcid":"https://orcid.org/0000-0002-1762-3277"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Apratim Mukherjee","raw_affiliation_strings":["Worcester Polytechnic Institute,Robotics Engineering,Worcester,MA,USA","Robotics Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute,Robotics Engineering,Worcester,MA,USA","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Robotics Engineering, Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034543991","display_name":"Carlo Pinciroli","orcid":"https://orcid.org/0000-0002-2155-0445"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlo Pinciroli","raw_affiliation_strings":["Worcester Polytechnic Institute,Robotics Engineering,Worcester,MA,USA","Robotics Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute,Robotics Engineering,Worcester,MA,USA","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Robotics Engineering, Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8854","last_page":"8861"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9937999844551086,"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"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8294554352760315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7442709803581238},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.7056717276573181},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6610731482505798},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6167025566101074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5976424813270569},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4864030182361603},{"id":"https://openalex.org/keywords/swarm-robotics","display_name":"Swarm robotics","score":0.4762803912162781},{"id":"https://openalex.org/keywords/interdependence","display_name":"Interdependence","score":0.4331170320510864},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.42513924837112427},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4244944751262665},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4227112829685211},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37118786573410034},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3499867022037506},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09147757291793823}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8294554352760315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442709803581238},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.7056717276573181},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6610731482505798},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6167025566101074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5976424813270569},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4864030182361603},{"id":"https://openalex.org/C169337768","wikidata":"https://www.wikidata.org/wiki/Q2446723","display_name":"Swarm robotics","level":3,"score":0.4762803912162781},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.4331170320510864},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.42513924837112427},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4244944751262665},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4227112829685211},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37118786573410034},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3499867022037506},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09147757291793823},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341563","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2017150251","https://openalex.org/W2050484682","https://openalex.org/W2052142439","https://openalex.org/W2096480305","https://openalex.org/W2102746067","https://openalex.org/W2141538250","https://openalex.org/W2145339207","https://openalex.org/W2159341149","https://openalex.org/W2296073425","https://openalex.org/W2395575420","https://openalex.org/W2567377301","https://openalex.org/W2626637010","https://openalex.org/W2746553466","https://openalex.org/W2805031923","https://openalex.org/W2891076394","https://openalex.org/W2914351253","https://openalex.org/W2924816077","https://openalex.org/W2949464762","https://openalex.org/W2950872548","https://openalex.org/W2963009616","https://openalex.org/W2963065757","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964251366","https://openalex.org/W2975703112","https://openalex.org/W2978148161","https://openalex.org/W2981038142","https://openalex.org/W3037550388","https://openalex.org/W3088990421","https://openalex.org/W3091470406","https://openalex.org/W3156295478","https://openalex.org/W3177398585","https://openalex.org/W3206518075","https://openalex.org/W3211352205","https://openalex.org/W4286748781","https://openalex.org/W4295598622","https://openalex.org/W4297795161","https://openalex.org/W4299802797","https://openalex.org/W4320561151","https://openalex.org/W6712181171","https://openalex.org/W6748839928","https://openalex.org/W6779557894"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2171408034","https://openalex.org/W3003320923","https://openalex.org/W2106140982","https://openalex.org/W2152313554","https://openalex.org/W2064303750","https://openalex.org/W1509300825","https://openalex.org/W3092582874","https://openalex.org/W2338718585","https://openalex.org/W2054620577"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,179],"learning":[2,180],"(DRL)":[3],"has":[4],"seen":[5],"re-markable":[6],"success":[7],"in":[8,43,71,182],"the":[9,58,79,97,120,122,138,143,160,189,193],"control":[10],"of":[11,51,99,192],"single":[12],"robots.":[13],"However,":[14],"applying":[15],"DRL":[16],"to":[17,77,96,116,130,140,155,195],"robot":[18],"swarms":[19],"presents":[20],"significant":[21],"challenges.":[22],"A":[23],"critical":[24],"challenge":[25],"is":[26],"non-stationarity,":[27],"which":[28],"occurs":[29],"when":[30,217],"two":[31,114],"or":[32,37],"more":[33],"robots":[34,59,123],"update":[35],"individual":[36],"shared":[38],"policies":[39],"concurrently,":[40],"thereby":[41],"engaging":[42],"an":[44,204],"interdependent":[45],"training":[46,57],"process":[47],"with":[48,60,184,219],"no":[49,125],"guarantees":[50],"convergence.":[52],"Circumventing":[53],"non-stationarity":[54],"typically":[55],"involves":[56],"global":[61,82,100,223],"information":[62],"about":[63],"other":[64,103],"agents'":[65],"states":[66],"and/or":[67],"actions.":[68],"In":[69,119,142],"contrast,":[70],"this":[72],"paper":[73],"we":[74,112,146,207],"explore":[75],"how":[76],"remove":[78],"need":[80],"for":[81],"information.":[83],"We":[84,170],"pose":[85],"our":[86],"problem":[87],"as":[88,108,162,188],"a":[89,109,152,157,163,172,196,200],"Partially":[90],"Observable":[91],"Markov":[92],"Decision":[93],"Process,":[94],"due":[95],"absence":[98],"knowledge":[101],"on":[102,132,137],"agents.":[104],"Using":[105],"collective":[106],"transport":[107,191],"testbed":[110],"scenario,":[111],"study":[113,174],"approaches":[115],"multi-agent":[117],"training.":[118],"first,":[121],"exchange":[124],"messages,":[126],"and":[127,165,214],"are":[128],"trained":[129,154],"rely":[131],"implicit":[133],"communication":[134],"through":[135],"push-and-pull":[136],"object":[139,194],"transport.":[141],"second":[144],"approach,":[145],"introduce":[147],"Global":[148],"State":[149],"Prediction":[150],"(GSP),":[151],"network":[153],"form":[156],"belief":[158],"over":[159,175],"swarm":[161],"whole":[164],"predict":[166],"its":[167],"future":[168],"states.":[169],"provide":[171],"comprehensive":[173],"four":[176],"well-known":[177],"deep":[178],"algorithms":[181],"environments":[183],"obstacles,":[185],"measuring":[186],"performance":[187,213],"successful":[190],"goal":[197],"location":[198],"within":[199],"desired":[201],"time-frame.":[202],"Through":[203],"ablation":[205],"study,":[206],"show":[208],"that":[209,221],"including":[210],"GSP":[211],"boosts":[212],"increases":[215],"robustness":[216],"compared":[218],"methods":[220],"use":[222],"knowledge.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}