{"id":"https://openalex.org/W7115180357","doi":"https://doi.org/10.5555/3535850.3535915","title":"Multiagent Model-Based Credit Assignment for Continuous Control","display_name":"Multiagent Model-Based Credit Assignment for Continuous Control","publication_year":2022,"publication_date":"2022-05-09","ids":{"openalex":"https://openalex.org/W7115180357","doi":"https://doi.org/10.5555/3535850.3535915"},"language":"en","primary_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/35f8f572-2043-4ac6-8206-72f2ed623b28","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/35f8f572-2043-4ac6-8206-72f2ed623b28","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Han, D, Lu, C X, Michalak, T & Wooldridge, M 2022, Multiagent Model-Based Credit Assignment for Continuous Control. in Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems. AAMAS '22, pp. 571\u2013579, 21st International Conference on Autonomous Agents and Multiagent Systems , Auckland, New Zealand, 9/05/22. https://doi.org/10.5555/3535850.3535915","raw_type":"contributionToPeriodical"},"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/35f8f572-2043-4ac6-8206-72f2ed623b28","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Han, Dongge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Dongge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lu, Chris Xiaoxuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Chris Xiaoxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Michalak, Tomasz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michalak, Tomasz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Wooldridge, Michael","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wooldridge, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.6898000240325928,"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":0.6898000240325928,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.05860000103712082,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.05220000073313713,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8888000249862671},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5428000092506409},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4505000114440918},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.40290001034736633},{"id":"https://openalex.org/keywords/decentralised-system","display_name":"Decentralised system","score":0.36800000071525574},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.34689998626708984},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.32089999318122864}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8888000249862671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692300021648407},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44359999895095825},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.36800000071525574},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3167000114917755},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:pure.ed.ac.uk:openaire/35f8f572-2043-4ac6-8206-72f2ed623b28","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/35f8f572-2043-4ac6-8206-72f2ed623b28","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Han, D, Lu, C X, Michalak, T & Wooldridge, M 2022, Multiagent Model-Based Credit Assignment for Continuous Control. in Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems. AAMAS '22, pp. 571\u2013579, 21st International Conference on Autonomous Agents and Multiagent Systems , Auckland, New Zealand, 9/05/22. https://doi.org/10.5555/3535850.3535915","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/35f8f572-2043-4ac6-8206-72f2ed623b28","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/35f8f572-2043-4ac6-8206-72f2ed623b28","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Han, D, Lu, C X, Michalak, T & Wooldridge, M 2022, Multiagent Model-Based Credit Assignment for Continuous Control. in Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems. AAMAS '22, pp. 571\u2013579, 21st International Conference on Autonomous Agents and Multiagent Systems , Auckland, New Zealand, 9/05/22. https://doi.org/10.5555/3535850.3535915","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.41475898027420044,"id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G4511761941","display_name":null,"funder_award_id":"EP/W002949/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,80],"learning":[2,24,81],"(RL)":[3],"has":[4],"recently":[5],"shown":[6],"great":[7],"promise":[8],"in":[9,17,42,48,164],"robotic":[10,66],"continuous":[11,84],"control":[12,179],"tasks.":[13,180],"Nevertheless,":[14],"prior":[15],"research":[16],"this":[18,74,87,127],"vein":[19],"center":[20],"around":[21],"the":[22,30,35,43,110,171],"centralized":[23,100],"setting":[25],"that":[26,97],"largely":[27],"relies":[28],"on":[29,176],"communication":[31,53],"availability":[32],"among":[33],"all":[34],"components":[36,67],"of":[37,71,173],"a":[38,49,69,77,92,114,132,150],"robot.":[39],"However,":[40,109],"agents":[41],"real":[44],"world":[45],"often":[46],"operate":[47],"decentralised":[50,72,78,105],"fashion":[51],"without":[52],"due":[54],"to":[55,161],"latency":[56],"requirements,":[57],"limited":[58],"power":[59],"budgets":[60],"and":[61,104],"safety":[62],"concerns.":[63],"By":[64],"formulating":[65],"as":[68],"system":[70,111],"agents,":[73],"work":[75],"presents":[76],"multiagent":[79,94],"framework":[82,96,137,175],"for":[83,99],"control.":[85],"To":[86,125],"end,":[88],"we":[89,129,147,168],"first":[90],"develop":[91],"cooperative":[93],"PPO":[95],"allows":[98],"optimisation":[101],"during":[102,107],"training":[103],"operation":[106],"execution.":[108],"only":[112],"receives":[113],"global":[115],"reward":[116,141],"signal":[117],"which":[118,138,159],"is":[119],"not":[120,145],"attributed":[121],"towards":[122],"each":[123],"agent.":[124],"address":[126],"challenge,":[128],"further":[130],"propose":[131],"generic":[133],"game-theoretic":[134],"credit":[135,156],"assignment":[136,157],"computes":[139],"agent-specific":[140],"signals.":[142],"Last":[143],"but":[144],"least,":[146],"also":[148],"incorporate":[149],"model-based":[151],"RL":[152],"module":[153],"into":[154],"our":[155,174],"framework,":[158],"leads":[160],"significant":[162],"improvement":[163],"sample":[165],"efficiency.":[166],"Finally,":[167],"empirically":[169],"demonstrate":[170],"effectiveness":[172],"Mujoco":[177],"locomotion":[178]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-15T00:00:00"}