{"id":"https://openalex.org/W4414432820","doi":"https://doi.org/10.1109/case58245.2025.11163870","title":"Benchmarking Population-Based Reinforcement Learning across Robotic Tasks with GPU-Accelerated Simulation","display_name":"Benchmarking Population-Based Reinforcement Learning across Robotic Tasks with GPU-Accelerated Simulation","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414432820","doi":"https://doi.org/10.1109/case58245.2025.11163870"},"language":"en","primary_location":{"id":"doi:10.1109/case58245.2025.11163870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","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/A5003810719","display_name":"Asad Ali Shahid","orcid":"https://orcid.org/0009-0001-0312-9657"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Asad Ali Shahid","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence, IDSIA USI-SUPSI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence, IDSIA USI-SUPSI","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043295239","display_name":"Yashraj Narang","orcid":"https://orcid.org/0000-0001-5445-3759"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yashraj Narang","raw_affiliation_strings":["NVIDIA Corporation,Santa Clara,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010287333","display_name":"Vincenzo Petrone","orcid":"https://orcid.org/0000-0003-4777-1761"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Vincenzo Petrone","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence, IDSIA USI-SUPSI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence, IDSIA USI-SUPSI","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012694169","display_name":"Enrico Ferrentino","orcid":"https://orcid.org/0000-0003-0768-8541"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enrico Ferrentino","raw_affiliation_strings":["University of Salerno,Fisciano,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Salerno,Fisciano,Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055942061","display_name":"Ankur Handa","orcid":"https://orcid.org/0000-0001-5170-1323"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Handa","raw_affiliation_strings":["NVIDIA Corporation,Santa Clara,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108257764","display_name":"Dieter Fox","orcid":"https://orcid.org/0009-0009-4694-9127"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dieter Fox","raw_affiliation_strings":["NVIDIA Corporation,Santa Clara,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050003000","display_name":"Marco Pavone","orcid":"https://orcid.org/0000-0002-0206-4337"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Pavone","raw_affiliation_strings":["Stanford University,Stanford,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086291668","display_name":"Loris Roveda","orcid":"https://orcid.org/0000-0002-4427-536X"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Loris Roveda","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence, IDSIA USI-SUPSI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence, IDSIA USI-SUPSI","institution_ids":["https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13138233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1231","last_page":"1238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9750999808311462,"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":0.9750999808311462,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9409999847412109,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.919700026512146,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.881600022315979},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.659500002861023},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6581000089645386},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4652000069618225},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4546000063419342},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3971000015735626},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.36079999804496765},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.357699990272522},{"id":"https://openalex.org/keywords/shadow","display_name":"Shadow (psychology)","score":0.34549999237060547}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.881600022315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6952000260353088},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.659500002861023},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6581000089645386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6295999884605408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6003999710083008},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C117797892","wikidata":"https://www.wikidata.org/wiki/Q286363","display_name":"Shadow (psychology)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/case58245.2025.11163870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1298441","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1298441","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2112474089","https://openalex.org/W2151083897","https://openalex.org/W2158782408","https://openalex.org/W2159721734","https://openalex.org/W2810602713","https://openalex.org/W2902907165","https://openalex.org/W2911087563","https://openalex.org/W2963150697","https://openalex.org/W2963544079","https://openalex.org/W2968116426","https://openalex.org/W2973229164","https://openalex.org/W2982316857","https://openalex.org/W2990747716","https://openalex.org/W3194048684","https://openalex.org/W3211145209","https://openalex.org/W4205430897","https://openalex.org/W4210939259","https://openalex.org/W4224903718","https://openalex.org/W4283787029","https://openalex.org/W4283788634","https://openalex.org/W4383108265","https://openalex.org/W4385430467","https://openalex.org/W4385430700","https://openalex.org/W4405304880","https://openalex.org/W4407316179","https://openalex.org/W4407736298","https://openalex.org/W4407948691"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"deep":[3],"reinforcement":[4],"learning":[5,37,106],"(RL)":[6],"has":[7],"shown":[8],"its":[9],"effectiveness":[10],"in":[11,80,116,150,167],"solving":[12],"complex":[13],"continuous":[14],"control":[15],"tasks.":[16],"However,":[17],"this":[18,180],"comes":[19],"at":[20],"the":[21,34,40,70,103,131,161,168,182,197],"cost":[22],"of":[23,27,36,51,73,105,133,152,196],"an":[24],"enormous":[25],"amount":[26],"experience":[28],"required":[29],"for":[30,139,171,186],"training,":[31],"exacerbated":[32],"by":[33,75,129],"sensitivity":[35],"efficiency":[38],"and":[39,63,95,136,194],"policy":[41],"performance":[42,104],"to":[43,68,156],"hyperparameter":[44],"selection,":[45],"which":[46],"often":[47],"requires":[48],"numerous":[49],"trials":[50],"time-consuming":[52],"experiments.":[53],"This":[54],"work":[55],"leverages":[56],"a":[57,64,172],"Population-Based":[58],"Reinforcement":[59],"Learning":[60],"(PBRL)":[61],"approach":[62],"GPU-accelerated":[65],"physics":[66],"simulator":[67],"enhance":[69],"exploration":[71],"capabilities":[72],"RL":[74,90],"concurrently":[76],"training":[77],"multiple":[78],"policies":[79,199],"parallel.":[81],"The":[82,108,141],"PBRL":[83,145,188],"framework":[84],"is":[85,181],"benchmarked":[86],"against":[87],"three":[88],"state-of-the-art":[89],"algorithms":[91],"\u2013":[92,97,119,128],"PPO,":[93],"SAC,":[94],"DDPG":[96],"dynamically":[98],"adjusting":[99],"hyperparameters":[100],"based":[101],"on":[102,112,190,202],"agents.":[107,159],"experiments":[109],"are":[110,164,200],"performed":[111],"four":[113],"challenging":[114],"tasks":[115],"Isaac":[117],"Gym":[118],"Anymal":[120],"Terrain,":[121],"Shadow":[122],"Hand,":[123],"Humanoid,":[124],"Franka":[125,173],"Nut":[126,174],"Pick":[127,175],"analyzing":[130],"effect":[132],"population":[134],"size":[135],"mutation":[137],"mechanisms":[138],"hyperpa-rameters.":[140],"results":[142],"show":[143],"that":[144],"agents":[146,163,189],"achieve":[147],"superior":[148],"performance,":[149],"terms":[151],"cumulative":[153],"reward,":[154],"compared":[155],"non-evolutionary":[157],"baseline":[158],"Moreover,":[160],"trained":[162],"finally":[165],"deployed":[166],"real":[169,191],"world":[170],"task.":[176],"To":[177],"our":[178,203],"knowledge,":[179],"first":[183],"sim-to-real":[184],"attempt":[185],"deploying":[187],"hardware.":[192],"Code":[193],"videos":[195],"learned":[198],"available":[201],"project":[204],"website.":[205]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}