{"id":"https://openalex.org/W4400951049","doi":"https://doi.org/10.1007/s10846-024-02138-8","title":"Adaptive Optimization of Hyper-Parameters for Robotic Manipulation through Evolutionary Reinforcement Learning","display_name":"Adaptive Optimization of Hyper-Parameters for Robotic Manipulation through Evolutionary Reinforcement Learning","publication_year":2024,"publication_date":"2024-07-24","ids":{"openalex":"https://openalex.org/W4400951049","doi":"https://doi.org/10.1007/s10846-024-02138-8"},"language":"en","primary_location":{"id":"doi:10.1007/s10846-024-02138-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10846-024-02138-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10846-024-02138-8.pdf","source":{"id":"https://openalex.org/S91329792","display_name":"Journal of Intelligent & Robotic Systems","issn_l":"0921-0296","issn":["0921-0296","1573-0409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Robotic Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10846-024-02138-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105017336","display_name":"Giulio Onori","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giulio Onori","raw_affiliation_strings":["Department of Mechanical Engineering, Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003810719","display_name":"Asad Ali Shahid","orcid":"https://orcid.org/0009-0001-0312-9657"},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"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":["Istituto Dalle Molle di studi sull\u2019intelligenza artificiale (IDSIA USI-SUPSI), Scuola universitaria professionale della Svizzera italiana, Lugano, CH 6962, Switzerland","Istituto Dalle Molle di studi sull'intelligenza artificiale (IDSIA USI-SUPSI), Scuola universitaria professionale della Svizzera italiana, Lugano, CH 6962, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Dalle Molle di studi sull\u2019intelligenza artificiale (IDSIA USI-SUPSI), Scuola universitaria professionale della Svizzera italiana, Lugano, CH 6962, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Istituto Dalle Molle di studi sull'intelligenza artificiale (IDSIA USI-SUPSI), Scuola universitaria professionale della Svizzera italiana, Lugano, CH 6962, Switzerland","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050750282","display_name":"Francesco Braghin","orcid":"https://orcid.org/0000-0002-0476-4118"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Braghin","raw_affiliation_strings":["Department of Mechanical Engineering, Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"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/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"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":true,"raw_author_name":"Loris Roveda","raw_affiliation_strings":["Istituto Dalle Molle di studi sull\u2019intelligenza artificiale (IDSIA USI-SUPSI), Scuola universitaria professionale della Svizzera italiana, Lugano, CH 6962, Switzerland","Istituto Dalle Molle di studi sull'intelligenza artificiale (IDSIA USI-SUPSI), Scuola universitaria professionale della Svizzera italiana, Lugano, CH 6962, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-4427-536X","affiliations":[{"raw_affiliation_string":"Istituto Dalle Molle di studi sull\u2019intelligenza artificiale (IDSIA USI-SUPSI), Scuola universitaria professionale della Svizzera italiana, Lugano, CH 6962, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Istituto Dalle Molle di studi sull'intelligenza artificiale (IDSIA USI-SUPSI), Scuola universitaria professionale della Svizzera italiana, Lugano, CH 6962, Switzerland","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086291668"],"corresponding_institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":1.7011,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85983144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"110","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980999827384949,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8434571623802185},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.6908646821975708},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6841577291488647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6788681745529175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6700384020805359},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6365239024162292},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5280020236968994},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.44905921816825867},{"id":"https://openalex.org/keywords/evolutionary-robotics","display_name":"Evolutionary robotics","score":0.41390717029571533},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0772048830986023}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8434571623802185},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.6908646821975708},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6841577291488647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6788681745529175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6700384020805359},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6365239024162292},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5280020236968994},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.44905921816825867},{"id":"https://openalex.org/C199505168","wikidata":"https://www.wikidata.org/wiki/Q3267529","display_name":"Evolutionary robotics","level":3,"score":0.41390717029571533},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0772048830986023},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10846-024-02138-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10846-024-02138-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10846-024-02138-8.pdf","source":{"id":"https://openalex.org/S91329792","display_name":"Journal of Intelligent & Robotic Systems","issn_l":"0921-0296","issn":["0921-0296","1573-0409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Robotic Systems","raw_type":"journal-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1278425","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1278425","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/article"}],"best_oa_location":{"id":"doi:10.1007/s10846-024-02138-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10846-024-02138-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10846-024-02138-8.pdf","source":{"id":"https://openalex.org/S91329792","display_name":"Journal of Intelligent & Robotic Systems","issn_l":"0921-0296","issn":["0921-0296","1573-0409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Robotic Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321942","display_name":"Hasler Stiftung","ror":"https://ror.org/04m3t9183"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400951049.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W6044743","https://openalex.org/W758372786","https://openalex.org/W1977655452","https://openalex.org/W2071810814","https://openalex.org/W2099746672","https://openalex.org/W2103196307","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2168661995","https://openalex.org/W2257979135","https://openalex.org/W2500624988","https://openalex.org/W2525203296","https://openalex.org/W2736601468","https://openalex.org/W2791006300","https://openalex.org/W2907904605","https://openalex.org/W2951278471","https://openalex.org/W2964166963","https://openalex.org/W3001500946","https://openalex.org/W3021933818","https://openalex.org/W3082636462","https://openalex.org/W3092022274","https://openalex.org/W3099303207","https://openalex.org/W3113139432","https://openalex.org/W3123139944","https://openalex.org/W3175558129","https://openalex.org/W3197703033","https://openalex.org/W3197886029","https://openalex.org/W3206921000","https://openalex.org/W4205432429","https://openalex.org/W4210939259","https://openalex.org/W4223437039","https://openalex.org/W4226145847","https://openalex.org/W4281807998","https://openalex.org/W4289253811","https://openalex.org/W4322490800","https://openalex.org/W4365145202","https://openalex.org/W4365396134","https://openalex.org/W4385451016","https://openalex.org/W4388031272","https://openalex.org/W4394007357","https://openalex.org/W4394662461"],"related_works":["https://openalex.org/W2130703626","https://openalex.org/W1954640725","https://openalex.org/W4297582752","https://openalex.org/W4285805405","https://openalex.org/W2391924736","https://openalex.org/W3133779647","https://openalex.org/W1560122427","https://openalex.org/W2021957875","https://openalex.org/W2802808995","https://openalex.org/W4381586542"],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"Reinforcement":[2],"Learning":[3],"applications":[4],"are":[5],"growing":[6],"due":[7],"to":[8,59,120,142,180],"their":[9],"capability":[10],"of":[11,28,32,42,52,74,103,124,153,169],"teaching":[12],"the":[13,20,26,37,40,71,100,104,114,121,145,150,156,159,167],"agent":[14,130],"any":[15],"task":[16],"autonomously":[17],"and":[18,34,54],"generalizing":[19],"learning.":[21],"However,":[22],"this":[23,61,63],"comes":[24],"at":[25],"cost":[27],"a":[29,49,108,125,177],"large":[30],"number":[31],"samples":[33,141],"interactions":[35],"with":[36,89,118],"environment.":[38],"Moreover,":[39],"robustness":[41],"learned":[43],"policies":[44],"is":[45,78,116],"usually":[46],"achieved":[47,94],"by":[48,149],"tedious":[50],"tuning":[51],"hyper-parameters":[53],"reward":[55,171,182],"functions.":[56,183],"In":[57,112],"order":[58],"address":[60],"issue,":[62],"paper":[64],"proposes":[65],"an":[66,81,90,97],"evolutionary":[67,91,129,160],"RL":[68,105],"algorithm":[69],"for":[70],"adaptive":[72,151],"optimization":[73],"hyper-parameters.":[75],"The":[76,93,128,162],"policy":[77],"trained":[79],"using":[80],"on-policy":[82],"algorithm,":[83],"Proximal":[84],"Policy":[85],"Optimization":[86],"(PPO),":[87],"coupled":[88],"algorithm.":[92,161],"results":[95],"demonstrate":[96],"improvement":[98],"in":[99],"sample":[101],"efficiency":[102],"training":[106],"on":[107],"robotic":[109],"grasping":[110,146],"task.":[111],"particular,":[113],"learning":[115],"improved":[117],"respect":[119],"baseline":[122],"case":[123],"non-evolutionary":[126],"agent.":[127],"needs":[131],"$$60$$":[132],"<mml:math":[133],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[134],"<mml:mrow>":[135],"<mml:mn>60</mml:mn>":[136],"</mml:mrow>":[137],"</mml:math>":[138],"%":[139],"fewer":[140],"completely":[143],"learn":[144],"task,":[147],"enabled":[148],"transfer":[152],"knowledge":[154],"between":[155],"agents":[157],"through":[158],"proposed":[163],"approach":[164,179],"also":[165],"demonstrates":[166],"possibility":[168],"updating":[170],"parameters":[172],"during":[173],"training,":[174],"potentially":[175],"providing":[176],"general":[178],"creating":[181]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
