{"id":"https://openalex.org/W7166324142","doi":"https://doi.org/10.1007/s44163-026-01642-0","title":"A multi-agent reinforcement learning algorithm for collaborative skill transfer in physical education","display_name":"A multi-agent reinforcement learning algorithm for collaborative skill transfer in physical education","publication_year":2026,"publication_date":"2026-06-28","ids":{"openalex":"https://openalex.org/W7166324142","doi":"https://doi.org/10.1007/s44163-026-01642-0"},"language":"en","primary_location":{"id":"doi:10.1007/s44163-026-01642-0","doi":"https://doi.org/10.1007/s44163-026-01642-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-026-01642-0","pdf_url":null,"source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s44163-026-01642-0","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139486203","display_name":"Hui Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Ma","raw_affiliation_strings":["School of Physical Education, Inner Mongolia University, Hohhot, 010020, Inner Mongolia Autonomous Region, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Physical Education, Inner Mongolia University, Hohhot, 010020, Inner Mongolia Autonomous Region, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139480483","display_name":"Bing Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405281709","display_name":"Chengde College of Applied Technology","ror":"https://ror.org/04rrk1334","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405281709"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bing Liu","raw_affiliation_strings":["Chengde College of Applied Technology, Chengde, 067000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chengde College of Applied Technology, Chengde, 067000, China","institution_ids":["https://openalex.org/I4405281709"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5139480483"],"corresponding_institution_ids":["https://openalex.org/I4405281709"],"apc_list":{"value":1590,"currency":"USD","value_usd":1590},"apc_paid":{"value":1590,"currency":"USD","value_usd":1590},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48593756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"1","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":0.635699987411499,"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":0.635699987411499,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.2728999853134155,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12290","display_name":"Human Motion and Animation","score":0.032999999821186066,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9819999933242798},{"id":"https://openalex.org/keywords/skill-transfer","display_name":"skill transfer","score":0.8700000047683716},{"id":"https://openalex.org/keywords/physical-education","display_name":"physical education","score":0.9399999976158142},{"id":"https://openalex.org/keywords/interlimb-coordination","display_name":"interlimb coordination","score":0.8650000095367432},{"id":"https://openalex.org/keywords/skeletal-tracking","display_name":"skeleton tracking","score":0.7049999833106995},{"id":"https://openalex.org/keywords/multi-agent-markov-decision-process","display_name":"multi-agent Markov decision process","score":0.6859999895095825}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6985999941825867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6733999848365784},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6675999760627747},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6643000245094299},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5595999956130981},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47870001196861267},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4756999909877777},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46720001101493835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4447999894618988},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2644999921321869}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44163-026-01642-0","doi":"https://doi.org/10.1007/s44163-026-01642-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-026-01642-0","pdf_url":null,"source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cc7e529935b041b0804e7bb86dff98f6","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/cc7e529935b041b0804e7bb86dff98f6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Discover Artificial Intelligence, Vol 6, Iss 1 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44163-026-01642-0","doi":"https://doi.org/10.1007/s44163-026-01642-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-026-01642-0","pdf_url":null,"source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5385000109672546,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"sustainable_development_goals_aurora":[{"score":0.5655253529548645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2617547828","https://openalex.org/W2807741983","https://openalex.org/W4380152116","https://openalex.org/W4388096834","https://openalex.org/W4392200913","https://openalex.org/W4396733392","https://openalex.org/W4403553807","https://openalex.org/W4405996330","https://openalex.org/W4408623100","https://openalex.org/W4409276659","https://openalex.org/W4412476489","https://openalex.org/W4412536850","https://openalex.org/W4413826254","https://openalex.org/W4415203842","https://openalex.org/W4417209952","https://openalex.org/W7116813739","https://openalex.org/W7126245938","https://openalex.org/W7128804488","https://openalex.org/W7131066749"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"In":[1],"order":[2],"to":[3,48,84],"solve":[4],"the":[5,15,20,27,95,104],"problems":[6],"of":[7,17,22,29,36,107],"poor":[8],"inter-limb":[9],"coordination,":[10],"delayed":[11],"temporal":[12],"adjustment,":[13],"and":[14,34,64,78,115],"lack":[16],"stability":[18],"in":[19,111,118],"transfer":[21],"skills,":[23],"as":[24,26],"well":[25],"challenge":[28],"unifying":[30],"multimodal":[31],"motion":[32],"representation":[33],"quantification":[35],"cross-limb":[37],"contributions,":[38],"this":[39,57],"paper":[40],"proposes":[41],"a":[42,86,112,119],"multi-agent":[43,53,113,122],"reinforcement":[44],"learning":[45],"model":[46,58],"tailored":[47],"physical":[49],"education.":[50],"Based":[51],"on":[52],"Markov":[54],"decision":[55],"processes,":[56],"integrates":[59],"video":[60],"stream,":[61,63],"skeleton":[62],"kinematic":[65],"sequence":[66],"coding.":[67],"It":[68],"incorporates":[69],"spatio-temporal":[70],"graph":[71],"attention,":[72],"message":[73],"passing,":[74],"counterfactual":[75],"credit":[76],"allocation,":[77],"confidence":[79],"region":[80],"stabilization":[81],"control":[82],"mechanisms":[83],"form":[85],"\u201crepresentation\u2014decision\u2014feedback\u2014closed-loop":[87],"optimization\u201d":[88],"algorithmic":[89],"chain.":[90],"Experimental":[91],"results":[92],"show":[93],"that":[94],"model\u2019s":[96],"pose":[97],"error":[98],"()":[99],"is":[100],"2.33":[101],"pixels,":[102],"outperforming":[103],"3.87":[105],"pixels":[106,110,117],"single-agent,":[108],"3.42":[109],"system,":[114],"3.05":[116],"globally":[120],"shared":[121],"system.":[123]},"counts_by_year":[],"updated_date":"2026-09-22T17:25:34.749102","created_date":"2026-06-28T00:00:00"}