{"id":"https://openalex.org/W4416798515","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249318","title":"HasRL Robot: A Heterogeneous Asynchronous Reinforcement Learning System for High-Dimensional Bipedal Control","display_name":"HasRL Robot: A Heterogeneous Asynchronous Reinforcement Learning System for High-Dimensional Bipedal Control","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798515","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249318"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-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":"https://openalex.org/A5080428088","display_name":"Jonathan Mai","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Jingyang Mai","raw_affiliation_strings":["National University of Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109273309","display_name":"Ziqing Guo","orcid":"https://orcid.org/0009-0006-3999-2221"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zechen Guo","raw_affiliation_strings":["National University of Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016292956","display_name":"Zhengding Luo","orcid":"https://orcid.org/0000-0002-2694-5059"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhengding Luo","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101323765","display_name":"Haozhe Ma","orcid":"https://orcid.org/0009-0002-7645-0115"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haozhe Ma","raw_affiliation_strings":["National University of Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5080428088"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38749268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1423","last_page":"1428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.6194999814033508,"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":0.6194999814033508,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.23170000314712524,"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/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.012500000186264515,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7871999740600586},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5491999983787537},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5332000255584717},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5040000081062317},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.475600004196167},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.454800009727478},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41290000081062317},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.39160001277923584},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.36250001192092896}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7871999740600586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7070000171661377},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5491999983787537},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5332000255584717},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5012999773025513},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.454800009727478},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3765999972820282},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.36250001192092896},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.32919999957084656},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C151800584","wikidata":"https://www.wikidata.org/wiki/Q2370000","display_name":"Gait","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2948000133037567},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C82327864","wikidata":"https://www.wikidata.org/wiki/Q835100","display_name":"Intelligent control","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2964114602","https://openalex.org/W3003936490","https://openalex.org/W3176539729","https://openalex.org/W3206620955","https://openalex.org/W4402284121"],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"utilization":[1],"of":[2,95,134],"computational":[3,96,117],"resources":[4,97],"remains":[5],"a":[6,59],"central":[7],"challenge":[8],"in":[9,74,140],"reinforcement":[10],"learning":[11,22,49,63],"(RL)-based":[12],"locomotion":[13],"control,":[14],"especially":[15],"for":[16,65],"high-dimensional":[17],"bipedal":[18,66],"robots.":[19],"The":[20],"robot":[21],"process":[23],"typically":[24],"comprises":[25],"two":[26],"stages:":[27],"data":[28,39],"collection":[29,40],"through":[30],"environment":[31],"interaction":[32],"and":[33,81,98,128,136],"policy":[34,80],"optimization.":[35],"Among":[36],"these,":[37],"the":[38,44,79,88,132],"phase":[41],"is":[42,106],"considered":[43],"primary":[45],"bottleneck":[46],"limiting":[47],"overall":[48,100],"speed.":[50],"To":[51],"address":[52],"these":[53],"challenges,":[54],"we":[55],"present":[56],"HasRL":[57,123],"Robot,":[58],"heterogeneous":[60],"asynchronous":[61],"RL-based":[62],"system":[64],"locomotion.":[67],"In":[68],"this":[69],"framework,":[70],"trajectories":[71],"are":[72,84],"collected":[73],"parallel":[75],"across":[76],"CPUs,":[77],"while":[78],"value":[82],"networks":[83],"updated":[85],"asynchronously":[86],"on":[87,112],"GPUs.":[89],"This":[90],"design":[91],"enables":[92],"effective":[93],"use":[94],"improves":[99],"training":[101,127],"throughput.":[102],"Furthermore,":[103],"our":[104],"framework":[105],"extensible":[107],"to":[108],"other":[109],"RL-driven":[110],"tasks":[111],"high-performance":[113],"machines,":[114],"thereby":[115],"maximizing":[116],"efficiency.":[118],"Experimental":[119],"results":[120],"demonstrate":[121],"that":[122],"Robot":[124],"achieves":[125],"superior":[126],"testing":[129],"performance,":[130],"enabling":[131],"emergence":[133],"stable":[135],"human-like":[137],"gait":[138],"behaviors":[139],"simulation.":[141]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}