{"id":"https://openalex.org/W7140126142","doi":"https://doi.org/10.1109/tie.2026.3672826","title":"MI-MRL: A Meta-Reinforcement Learning Method Based on Memory Information for Bipedal Locomotion Task","display_name":"MI-MRL: A Meta-Reinforcement Learning Method Based on Memory Information for Bipedal Locomotion Task","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7140126142","doi":"https://doi.org/10.1109/tie.2026.3672826"},"language":"en","primary_location":{"id":"doi:10.1109/tie.2026.3672826","doi":"https://doi.org/10.1109/tie.2026.3672826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tie.2026.3672826","pdf_url":null,"source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-a","jufo-3","ki-jl-1","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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 Transactions on Industrial Electronics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5061662798","display_name":"Wenhao Tan","orcid":"https://orcid.org/0009-0006-4197-142X","observed_orcids":["https://orcid.org/0009-0006-4197-142X"]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Tan","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0006-4197-142X","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101081488","display_name":"Xing Fang","orcid":"https://orcid.org/0000-0002-9930-5845","observed_orcids":["https://orcid.org/0000-0002-9930-5845"]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Fang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-9930-5845","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130384104","display_name":"Yanyun Chen","orcid":"https://orcid.org/0000-0002-8449-046X","observed_orcids":["https://orcid.org/0000-0002-8449-046X"]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyun Chen","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-8449-046X","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050561793","display_name":"Zhiheng Li","orcid":"https://orcid.org/0000-0002-5288-4325","observed_orcids":["https://orcid.org/0000-0002-5288-4325"]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Li","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-5288-4325","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047100124","display_name":"Ran Song","orcid":"https://orcid.org/0000-0002-1344-4415","observed_orcids":["https://orcid.org/0000-0002-1344-4415"]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Song","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-1344-4415","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113122959","display_name":"Ruifeng Wang","orcid":"https://orcid.org/0009-0005-9432-5977","observed_orcids":["https://orcid.org/0009-0005-9432-5977","https://orcid.org/0000-0002-2512-120X"]},"institutions":[{"id":"https://openalex.org/I4405281134","display_name":"Jinan Preschool Education College","ror":"https://ror.org/03xmtbp93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405281134"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifeng Wang","raw_affiliation_strings":["Jinan Preschool Education College, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-2512-120X","affiliations":[{"raw_affiliation_string":"Jinan Preschool Education College, Jinan, China","institution_ids":["https://openalex.org/I4405281134"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108612761","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-4960-3190","observed_orcids":["https://orcid.org/0000-0002-4960-3190","https://orcid.org/0000-0002-3584-8541","https://orcid.org/0000-0003-2747-1622"]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-4960-3190","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"73","issue":"8","first_page":"11949","last_page":"11960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8134999871253967,"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":0.8134999871253967,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.16869999468326569,"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"}},{"id":"https://openalex.org/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.012000000104308128,"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/meta-reinforcement-learning","display_name":"meta-reinforcement learning","score":0.9700000286102295},{"id":"https://openalex.org/keywords/bipedal-locomotion","display_name":"bipedalism","score":0.9959999918937683},{"id":"https://openalex.org/keywords/sim-to-real-gap","display_name":"sim-to-real gap","score":0.9259999990463257},{"id":"https://openalex.org/keywords/state-estimation","display_name":"state estimation","score":0.6140000224113464},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"noise reduction","score":0.9570000171661377},{"id":"https://openalex.org/keywords/contextual-adaptation","display_name":"contextual adaptation","score":0.6510000228881836},{"id":"https://openalex.org/keywords/legged-robot-control","display_name":"legged robot control","score":0.6589999794960022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6717000007629395},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6629999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5548999905586243},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3806999921798706},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.33869999647140503},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30649998784065247},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C143733281","wikidata":"https://www.wikidata.org/wiki/Q372949","display_name":"Bipedalism","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tie.2026.3672826","doi":"https://doi.org/10.1109/tie.2026.3672826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tie.2026.3672826","pdf_url":null,"source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-a","jufo-3","ki-jl-1","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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 Transactions on Industrial Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6033659780","display_name":null,"funder_award_id":"U22A2057","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6689800364","display_name":null,"funder_award_id":"ZR2025ZD12","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2767050701","https://openalex.org/W2976047560","https://openalex.org/W3093922502","https://openalex.org/W3110378871","https://openalex.org/W3112664346","https://openalex.org/W3130568950","https://openalex.org/W3159360606","https://openalex.org/W3175254947","https://openalex.org/W3187710359","https://openalex.org/W3209381383","https://openalex.org/W4210939259","https://openalex.org/W4223604247","https://openalex.org/W4285203349","https://openalex.org/W4285741773","https://openalex.org/W4303647912","https://openalex.org/W4376481181","https://openalex.org/W4383109125","https://openalex.org/W4385430550","https://openalex.org/W4389974952","https://openalex.org/W4393050466","https://openalex.org/W4393144926","https://openalex.org/W4394872716","https://openalex.org/W4400644392","https://openalex.org/W4401070717","https://openalex.org/W4403864141","https://openalex.org/W4403864172","https://openalex.org/W4404638792","https://openalex.org/W4405632846","https://openalex.org/W4405785208","https://openalex.org/W4405785286","https://openalex.org/W4405787394","https://openalex.org/W4406522117","https://openalex.org/W4407948694","https://openalex.org/W4408258660"],"related_works":["https://openalex.org/W3032919895","https://openalex.org/W4223604247","https://openalex.org/W4390976912","https://openalex.org/W7151102895","https://openalex.org/W4389666172","https://openalex.org/W7160146270","https://openalex.org/W3080433414","https://openalex.org/W7090875381","https://openalex.org/W7128815034","https://openalex.org/W4377141222"],"abstract_inverted_index":{"Bipedal":[0],"locomotion":[1],"is":[2,153],"challenging":[3],"for":[4,46],"many":[5],"learning-based":[6],"algorithms.":[7,33],"The":[8,147],"sim-to-real":[9],"gap,":[10],"the":[11,17,29,63,73,83,86,91,118,143,166],"changes":[12,18,56,159],"in":[13,19,68,79,171],"task":[14],"loads,":[15],"and":[16,57,81,105,112,125,131,160],"joint":[20],"damping":[21],"caused":[22],"by":[23],"long-term":[24],"use":[25],"may":[26],"all":[27],"degrade":[28],"performance":[30],"of":[31,93,142],"these":[32],"Aiming":[34],"at":[35],"such":[36],"issues,":[37],"we":[38],"propose":[39],"a":[40,59,102,106,162],"memory-informed":[41],"meta-reinforcement":[42],"learning":[43],"(MI-MRL)":[44],"method":[45],"bipedal":[47],"locomotion.":[48],"MI-MRL":[49,99,121,152],"demonstrates":[50],"robustness":[51],"to":[52,62,85,96,109,117,155,165],"various":[53,156],"task-related":[54,157],"parameter":[55,158],"offers":[58,161],"practical":[60,163],"solution":[61,164],"difficulties":[64,167],"that":[65,141,151,168],"MRL":[66,80,169],"faces":[67,170],"real-world":[69,97,172],"deployment.":[70,173],"It":[71],"replaces":[72],"standard":[74],"feedback":[75],"rewards":[76],"commonly":[77],"used":[78],"restructures":[82],"input":[84],"context":[87,126],"encoder,":[88],"thus":[89],"broadening":[90],"applicability":[92],"MRL-based":[94,145],"methods":[95],"scenarios.":[98],"also":[100,149],"introduces":[101],"state":[103],"estimator":[104],"noise":[107],"filter":[108],"accelerate":[110],"training":[111],"enhance":[113],"algorithm":[114],"performance.":[115],"According":[116],"experimental":[119],"results,":[120],"completes":[122],"information":[123],"collection":[124],"adaptation":[127],"within":[128],"0.32":[129],"s,":[130],"achieves":[132],"an":[133],"external":[134],"load":[135],"tolerance":[136],"20":[137],"times":[138],"higher":[139],"than":[140],"latest":[144],"methods.":[146],"results":[148],"demonstrate":[150],"robust":[154]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}