{"id":"https://openalex.org/W3135457936","doi":"https://doi.org/10.1109/iros51168.2021.9635836","title":"MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models","display_name":"MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3135457936","doi":"https://doi.org/10.1109/iros51168.2021.9635836","mag":"3135457936"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9635836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9635836","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5065810966","display_name":"Dani\u00ebl Willemsen","orcid":"https://orcid.org/0000-0003-3943-5805"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Daniel Willemsen","raw_affiliation_strings":["Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048606189","display_name":"Mario Coppola","orcid":"https://orcid.org/0000-0003-4694-2960"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mario Coppola","raw_affiliation_strings":["Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058902676","display_name":"Guido de Croon","orcid":"https://orcid.org/0000-0001-8265-1496"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Guido C.H.E. de Croon","raw_affiliation_strings":["Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":2.0294,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.89186691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5635","last_page":"5640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9828000068664551,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9544000029563904,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8683832883834839},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743003785610199},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7388273477554321},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6966897249221802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6115756630897522},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5817384719848633},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4655395746231079},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41478079557418823}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8683832883834839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743003785610199},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7388273477554321},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6966897249221802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6115756630897522},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5817384719848633},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4655395746231079},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41478079557418823},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/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/iros51168.2021.9635836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9635836","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2602275733","https://openalex.org/W2605102758","https://openalex.org/W2766151966","https://openalex.org/W2805762288","https://openalex.org/W2894976951","https://openalex.org/W2911300280","https://openalex.org/W2951896791","https://openalex.org/W2953708620","https://openalex.org/W2962966033","https://openalex.org/W2963407617","https://openalex.org/W2963881016","https://openalex.org/W2970277495","https://openalex.org/W2997535522","https://openalex.org/W3011672202","https://openalex.org/W3093287223","https://openalex.org/W3163926178","https://openalex.org/W4231746564","https://openalex.org/W4235152929","https://openalex.org/W4288319859","https://openalex.org/W4295598622","https://openalex.org/W4298206671","https://openalex.org/W4299590935","https://openalex.org/W4299802797","https://openalex.org/W6736572398","https://openalex.org/W6738796088","https://openalex.org/W6749304979","https://openalex.org/W6751494529","https://openalex.org/W6755069753","https://openalex.org/W6758373747","https://openalex.org/W6764053384","https://openalex.org/W6764980988","https://openalex.org/W6772438481"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W4226283576","https://openalex.org/W4319083788","https://openalex.org/W3135457936","https://openalex.org/W4287281679"],"abstract_inverted_index":{"Multi-robot":[0],"systems":[1,83,142],"can":[2],"benefit":[3],"from":[4],"reinforcement":[5],"learning":[6,139],"(RL)":[7],"algorithms":[8,61],"that":[9],"learn":[10],"behaviours":[11],"in":[12,69],"a":[13,18,40,63,70,78,90,116],"small":[14],"number":[15],"of":[16,30,65,85],"trials,":[17],"property":[19,80],"known":[20],"as":[21],"sample":[22,36,96],"efficiency.":[23,37],"This":[24,76],"research":[25],"thus":[26],"investigates":[27],"the":[28,52],"use":[29],"learned":[31,91],"world":[32,92],"models":[33],"to":[34,67,94,99,119,126],"improve":[35,95],"We":[38,105],"present":[39],"novel":[41],"multi-agent":[42],"model-based":[43],"RL":[44],"algorithm:":[45],"Multi-Agent":[46,101],"Model-Based":[47],"Policy":[48],"Optimization":[49],"(MAMBPO),":[50],"utilizing":[51],"Centralized":[53],"Learning":[54],"for":[55,81,140],"Decentralized":[56],"Execution":[57],"(CLDE)":[58],"framework.":[59],"CLDE":[60],"allow":[62],"group":[64],"agents":[66],"act":[68],"fully":[71],"decentralized":[72],"manner":[73],"after":[74],"training.":[75],"is":[77],"desirable":[79],"many":[82],"comprising":[84],"multiple":[86],"robots.":[87],"MAMBPO":[88,114],"uses":[89],"model":[93],"efficiency":[97],"compared":[98],"model-free":[100],"Soft":[102],"Actor-Critic":[103],"(MASAC).":[104],"demonstrate":[106],"this":[107],"on":[108],"two":[109],"simulated":[110],"multi-robot":[111,141],"tasks,":[112],"where":[113],"achieves":[115],"similar":[117],"performance":[118],"MASAC,":[120],"but":[121],"requires":[122],"far":[123],"fewer":[124],"samples":[125],"do":[127],"so.":[128],"Through":[129],"this,":[130],"we":[131],"take":[132],"an":[133],"important":[134],"step":[135],"towards":[136],"making":[137],"real-life":[138],"possible.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}