{"id":"https://openalex.org/W4405710022","doi":"https://doi.org/10.1109/robot61475.2024.10796930","title":"Model-Based Policy Optimization for Legged Locomotion","display_name":"Model-Based Policy Optimization for Legged Locomotion","publication_year":2024,"publication_date":"2024-11-06","ids":{"openalex":"https://openalex.org/W4405710022","doi":"https://doi.org/10.1109/robot61475.2024.10796930"},"language":"en","primary_location":{"id":"doi:10.1109/robot61475.2024.10796930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot61475.2024.10796930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 7th Iberian Robotics Conference (ROBOT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5057290723","display_name":"Javier Garcia-Barcos","orcid":"https://orcid.org/0000-0001-7251-0753"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Garcia-Barcos","raw_affiliation_strings":["I3A, Universidad de Zaragoza,Zaragoza,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I3A, Universidad de Zaragoza,Zaragoza,Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049372967","display_name":"Rub\u00e9n Mart\u00ednez-Cant\u00edn","orcid":"https://orcid.org/0000-0002-6741-844X"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ruben Martinez-Cantin","raw_affiliation_strings":["I3A, Universidad de Zaragoza,Zaragoza,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I3A, Universidad de Zaragoza,Zaragoza,Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060302183","display_name":"Luis Montesano","orcid":"https://orcid.org/0000-0003-1183-349X"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Montesano","raw_affiliation_strings":["I3A, Universidad de Zaragoza,Zaragoza,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I3A, Universidad de Zaragoza,Zaragoza,Spain","institution_ids":["https://openalex.org/I255234318"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I255234318"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9296000003814697,"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"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9296000003814697,"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"}},{"id":"https://openalex.org/T12810","display_name":"Real-time simulation and control systems","score":0.9110000133514404,"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/computer-science","display_name":"Computer science","score":0.5916246175765991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5916246175765991}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robot61475.2024.10796930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot61475.2024.10796930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 7th Iberian Robotics Conference (ROBOT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W770013183","https://openalex.org/W1574246016","https://openalex.org/W1738827650","https://openalex.org/W1868320990","https://openalex.org/W2103328396","https://openalex.org/W2158782408","https://openalex.org/W2189982084","https://openalex.org/W2225156818","https://openalex.org/W2294316001","https://openalex.org/W2907537824","https://openalex.org/W2911546748","https://openalex.org/W4205197309","https://openalex.org/W4205513846","https://openalex.org/W4233157081","https://openalex.org/W6617145748","https://openalex.org/W6677916085","https://openalex.org/W6680657880","https://openalex.org/W6730042731","https://openalex.org/W6756192075","https://openalex.org/W6764053384","https://openalex.org/W6794067299"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"this":[1,76],"paper,":[2],"we":[3],"explore":[4],"model-based":[5],"reinforcement":[6],"learning":[7,25,31,73,122],"(MBRL)":[8],"for":[9,55,158],"legged":[10,102,159],"locomotion":[11,160],"in":[12,81,156],"robotics,":[13],"employing":[14],"state-of-the-art":[15,115],"techniques":[16],"to":[17,43,63],"evaluate":[18],"the":[19,24,50,69,72,109,131,149],"performance":[20,110],"and":[21,30,48,67,92,125,154,161],"stability":[22],"of":[23,71,88,111,114,121,133,151],"process":[26],"under":[27],"different":[28,89,112],"models":[29],"strategies.":[32],"Our":[33,105],"algorithm":[34],"utilizes":[35],"policy":[36,56],"search":[37],"methods,":[38],"specifically":[39],"leveraging":[40],"deep":[41,152],"ensembles":[42,59,153],"construct":[44],"a":[45,85,118],"dynamic":[46,97],"model":[47,65,98],"integrating":[49],"soft":[51],"actor-critic":[52],"(SAC)":[53],"framework":[54],"learning.":[57],"Deep":[58],"are":[60,138],"traditionally":[61],"employed":[62],"address":[64],"uncertainties":[66],"improve":[68],"robustness":[70],"process,":[74],"however,":[75],"relationship":[77],"is":[78],"barely":[79],"evaluated":[80],"practice.":[82],"We":[83],"conduct":[84],"comprehensive":[86],"comparison":[87],"architectural":[90],"designs":[91],"ensemble":[93],"strategies":[94,113],"within":[95],"our":[96],"on":[99],"several":[100],"simulated":[101],"robot":[103],"platforms.":[104],"evaluation":[106],"includes":[107],"benchmarking":[108],"algorithms,":[116],"providing":[117],"detailed":[119],"analysis":[120],"speed,":[123],"stability,":[124],"overall":[126],"effectiveness.":[127],"The":[128],"results":[129],"highlight":[130],"importance":[132],"certain":[134],"design":[135],"criteria":[136],"which":[137],"typically":[139],"assumed":[140],"as":[141],"granted.":[142],"This":[143],"study":[144],"provides":[145],"valuable":[146],"insights":[147],"into":[148],"application":[150],"SAC":[155],"MBRL":[157],"complex":[162],"robotic":[163],"control":[164],"systems.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}