{"id":"https://openalex.org/W4389924455","doi":"https://doi.org/10.1109/access.2023.3344393","title":"Comparative Analysis of Reinforcement Learning Algorithms for Bipedal Robot Locomotion","display_name":"Comparative Analysis of Reinforcement Learning Algorithms for Bipedal Robot Locomotion","publication_year":2023,"publication_date":"2023-12-18","ids":{"openalex":"https://openalex.org/W4389924455","doi":"https://doi.org/10.1109/access.2023.3344393"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3344393","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3344393","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10380310/10364844.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/10380310/10364844.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078177442","display_name":"\u00d6m\u00fcr Aydo\u011fmu\u015f","orcid":"https://orcid.org/0000-0001-8142-1146"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omur Aydogmus","raw_affiliation_strings":["Department of Mechatronics Engineering, Faculty of Technology, Fırat University, Elazig, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechatronics Engineering, Faculty of Technology, Fırat University, Elazig, Turkey","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058600834","display_name":"Musa Y\u0131lmaz","orcid":"https://orcid.org/0000-0002-2306-6008"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]},{"id":"https://openalex.org/I32481161","display_name":"Batman University","ror":"https://ror.org/051tsqh55","country_code":"TR","type":"education","lineage":["https://openalex.org/I32481161"]}],"countries":["TR","US"],"is_corresponding":false,"raw_author_name":"Musa Yilmaz","raw_affiliation_strings":["Center for Environmental Research and Technology, Bourns College of Engineering, University of California at Riverside, Riverside, CA, USA","Department of Electrical and Electronics Engineering, Batman University, Batman, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-2306-6008","affiliations":[{"raw_affiliation_string":"Center for Environmental Research and Technology, Bourns College of Engineering, University of California at Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, Batman University, Batman, Turkey","institution_ids":["https://openalex.org/I32481161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.5552,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.8188084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"7490","last_page":"7499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9998999834060669,"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":0.9998999834060669,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T10653","display_name":"Robot Manipulation and Learning","score":0.9901000261306763,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7260177135467529},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6897198557853699},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5144906044006348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45547863841056824},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33682361245155334}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7260177135467529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6897198557853699},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5144906044006348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45547863841056824},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33682361245155334}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2023.3344393","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3344393","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10380310/10364844.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt49q760h0","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/49q760h0","pdf_url":"https://escholarship.org/content/qt49q760h0/qt49q760h0.pdf?t=s889ea","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:doaj.org/article:40d2995c40e347a4aeb4307fed436f91","is_oa":true,"landing_page_url":"https://doaj.org/article/40d2995c40e347a4aeb4307fed436f91","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,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 7490-7499 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3344393","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3344393","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10380310/10364844.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389924455.pdf","grobid_xml":"https://content.openalex.org/works/W4389924455.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2899464658","https://openalex.org/W2935901025","https://openalex.org/W2939558708","https://openalex.org/W2949676527","https://openalex.org/W3015880599","https://openalex.org/W3081336937","https://openalex.org/W3085993909","https://openalex.org/W3096749928","https://openalex.org/W3130657420","https://openalex.org/W3131916177","https://openalex.org/W3154341275","https://openalex.org/W3171189531","https://openalex.org/W3206620955","https://openalex.org/W3207674611","https://openalex.org/W3211673469","https://openalex.org/W3217656104","https://openalex.org/W4205511942","https://openalex.org/W4212766024","https://openalex.org/W4214911315","https://openalex.org/W4221162532","https://openalex.org/W4282598937","https://openalex.org/W4292852808","https://openalex.org/W4309070979","https://openalex.org/W4317721968","https://openalex.org/W4367016688","https://openalex.org/W4386918912","https://openalex.org/W4387682164","https://openalex.org/W4387951956","https://openalex.org/W6676179485","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6783042659","https://openalex.org/W6810015666","https://openalex.org/W6811164566"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864","https://openalex.org/W2001405890"],"abstract_inverted_index":{"In":[0],"this":[1],"research,":[2],"an":[3,149,156,163,171],"optimization":[4,46,56,82,122,183],"methodology":[5],"was":[6,68],"introduced":[7],"for":[8,140],"improving":[9],"bipedal":[10,79,192],"robot":[11,193],"locomotion":[12,188],"controlled":[13],"by":[14],"reinforcement":[15],"learning":[16,90],"(RL)":[17],"algorithms.":[18,44,117],"Specifically,":[19],"the":[20,25,49,64,71,78,84,107,113,121,127,141,179,182,187,191],"study":[21,104],"focused":[22],"on":[23,112],"optimizing":[24],"Proximal":[26],"Policy":[27,41],"Optimization":[28],"(PPO),":[29],"Advantage":[30],"Actor-Critic":[31,34],"(A2C),":[32],"Soft":[33],"(SAC),":[35],"and":[36,75,99,168],"Twin":[37],"Delayed":[38],"Deep":[39],"Deterministic":[40],"Gradients":[42],"(TD3)":[43],"The":[45,81,103,118,136],"process":[47],"utilized":[48],"Tree-structured":[50],"Parzen":[51],"Estimator":[52],"(TPE),":[53],"a":[54],"Bayesian":[55],"technique.":[57],"All":[58],"RL":[59,116,129,195],"algorithms":[60,130],"were":[61,124,144],"applied":[62],"to":[63],"same":[65],"environment,":[66],"which":[67],"created":[69],"within":[70],"OpenAI":[72],"GYM":[73],"framework":[74],"known":[76],"as":[77,126,145],"walker.":[80],"involved":[83],"fine-tuning":[85],"of":[86,109,115,120,152,159,166,174,181,190],"key":[87],"hyperparameters,":[88],"including":[89],"rate,":[91],"discount":[92],"factor,":[93],"generalized":[94],"advantage":[95],"estimation,":[96],"entropy":[97],"coefficient,":[98],"Polyak":[100],"update":[101],"parameters.":[102],"comprehensively":[105],"analyzed":[106],"impact":[108],"these":[110],"hyperparameters":[111],"performance":[114],"results":[119],"efforts":[123],"promising,":[125],"fine-tuned":[128],"demonstrated":[131],"significant":[132],"improvements":[133],"in":[134,185],"performance.":[135],"mean":[137],"reward":[138,151,158,165,173],"values":[139],"10":[142],"trials":[143],"follows:":[146],"PPO":[147],"achieved":[148],"average":[150,157,164,172],"181.3,":[153],"A2C":[154],"obtained":[155],"\u2212122.2,":[160],"SAC":[161],"reached":[162],"320.3,":[167],"TD3":[169],"had":[170],"278.6.":[175],"These":[176],"outcomes":[177],"underscore":[178],"effectiveness":[180],"approach":[184],"enhancing":[186],"capabilities":[189],"using":[194],"techniques.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}