{"id":"https://openalex.org/W7083188390","doi":"https://doi.org/10.1109/lra.2025.3614078","title":"Learning Humanoid Arm Motion via Centroidal Momentum Regularized Multi-Agent Reinforcement Learning","display_name":"Learning Humanoid Arm Motion via Centroidal Momentum Regularized Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-24","ids":{"openalex":"https://openalex.org/W7083188390","doi":"https://doi.org/10.1109/lra.2025.3614078"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3614078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3614078","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-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":null,"display_name":"Ho Jae Lee","orcid":"https://orcid.org/0009-0001-2466-9636"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ho Jae Lee","raw_affiliation_strings":["Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0009-0001-2466-9636","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Se Hwan Jeon","orcid":"https://orcid.org/0000-0002-2791-7850"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Se Hwan Jeon","raw_affiliation_strings":["Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2791-7850","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sangbae Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sangbae Kim","raw_affiliation_strings":["Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2763,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95968123,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"10","issue":"11","first_page":"11968","last_page":"11975"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6459000110626221,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6459000110626221,"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/T13067","display_name":"Geological Modeling and Analysis","score":0.027899999171495438,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14311","display_name":"Electrical and Electromagnetic Research","score":0.021900000050663948,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.7472000122070312},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7153000235557556},{"id":"https://openalex.org/keywords/angular-momentum","display_name":"Angular momentum","score":0.5799999833106995},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5214999914169312},{"id":"https://openalex.org/keywords/terrain","display_name":"Terrain","score":0.4796999990940094},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.47540000081062317},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.47099998593330383},{"id":"https://openalex.org/keywords/torque","display_name":"Torque","score":0.4708000123500824},{"id":"https://openalex.org/keywords/ground-reaction-force","display_name":"Ground reaction force","score":0.46650001406669617},{"id":"https://openalex.org/keywords/swing","display_name":"Swing","score":0.44769999384880066}],"concepts":[{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7472000122070312},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7153000235557556},{"id":"https://openalex.org/C155675718","wikidata":"https://www.wikidata.org/wiki/Q161254","display_name":"Angular momentum","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5738000273704529},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5214999914169312},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4763000011444092},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C144171764","wikidata":"https://www.wikidata.org/wiki/Q48103","display_name":"Torque","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C96332660","wikidata":"https://www.wikidata.org/wiki/Q5610971","display_name":"Ground reaction force","level":3,"score":0.46650001406669617},{"id":"https://openalex.org/C65655974","wikidata":"https://www.wikidata.org/wiki/Q14867674","display_name":"Swing","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4399999976158142},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3398999869823456},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.32820001244544983},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C108439606","wikidata":"https://www.wikidata.org/wiki/Q3305038","display_name":"Angular displacement","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C5594486","wikidata":"https://www.wikidata.org/wiki/Q161635","display_name":"Angular velocity","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2892000079154968},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.2556999921798706},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3614078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3614078","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1661970104","https://openalex.org/W1968106150","https://openalex.org/W1973146638","https://openalex.org/W2061983716","https://openalex.org/W2118320757","https://openalex.org/W2125512581","https://openalex.org/W2143729862","https://openalex.org/W2146469560","https://openalex.org/W2617547828","https://openalex.org/W2739330054","https://openalex.org/W2842089854","https://openalex.org/W2906487027","https://openalex.org/W2981545385","https://openalex.org/W4214634122","https://openalex.org/W4229044820","https://openalex.org/W4285102639","https://openalex.org/W4367016688","https://openalex.org/W4385858056","https://openalex.org/W4390481038","https://openalex.org/W4394872716","https://openalex.org/W4401415103","https://openalex.org/W4405055865","https://openalex.org/W4405785534","https://openalex.org/W4405785558"],"related_works":[],"abstract_inverted_index":{"Humans":[0],"naturally":[1],"swing":[2],"their":[3],"arms":[4,51],"during":[5,111],"locomotion":[6,112,147],"to":[7,75,108],"regulate":[8],"whole-body":[9,34],"dynamics,":[10],"reduce":[11,98],"angular":[12,68,100],"momentum,":[13],"and":[14,52,66,91,102,121,155],"help":[15],"maintain":[16],"balance.":[17],"Inspired":[18],"by":[19,88],"this":[20],"principle,":[21],"we":[22,133],"present":[23],"a":[24],"limb-level":[25],"multi-agent":[26,123],"reinforcement":[27],"learning":[28],"(RL)":[29],"framework":[30],"that":[31,61,97],"enables":[32],"coordinated":[33],"control":[35],"of":[36,129],"humanoid":[37],"robots":[38],"through":[39,80],"emergent":[40],"arm":[41,85,95],"motion.":[42],"Our":[43],"approach":[44],"employs":[45],"separate":[46],"actor-critic":[47],"structures":[48],"for":[49],"the":[50,127,135,139],"legs,":[53],"trained":[54],"with":[55,119],"centralized":[56],"critics":[57],"but":[58],"decentralized":[59],"actors":[60],"share":[62],"only":[63],"base":[64],"states":[65],"centroidal":[67],"momentum":[69,101],"(CAM)":[70],"observations,":[71],"allowing":[72],"each":[73],"agent":[74,86],"specialize":[76],"in":[77],"task-relevant":[78],"behaviors":[79],"modular":[81],"reward":[82],"design.":[83],"The":[84],"guided":[87],"CAM":[89],"tracking":[90],"damping":[92],"rewards":[93],"promotes":[94],"motions":[96],"overall":[99],"vertical":[103],"ground":[104],"reaction":[105],"moments,":[106],"contributing":[107],"improved":[109],"balance":[110],"or":[113],"under":[114],"external":[115],"perturbations.":[116],"Comparative":[117],"studies":[118],"single-agent":[120],"alternative":[122],"baselines":[124],"further":[125],"validate":[126],"effectiveness":[128],"our":[130],"approach.":[131],"Finally,":[132],"deploy":[134],"learned":[136],"policy":[137],"on":[138],"MIT":[140],"Humanoid,":[141],"achieving":[142],"robust":[143],"performance":[144],"across":[145],"diverse":[146],"tasks,":[148],"including":[149],"flat-ground":[150],"walking,":[151],"rough":[152],"terrain":[153],"traversal,":[154],"stair":[156],"climbing.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
