{"id":"https://openalex.org/W2895279298","doi":"https://doi.org/10.1109/mlsp49062.2020.9231618","title":"PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptation","display_name":"PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptation","publication_year":2020,"publication_date":"2020-09-01","ids":{"openalex":"https://openalex.org/W2895279298","doi":"https://doi.org/10.1109/mlsp49062.2020.9231618","mag":"2895279298"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp49062.2020.9231618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp49062.2020.9231618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1810.02541","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060951467","display_name":"Perttu H\u00e4m\u00e4l\u00e4inen","orcid":"https://orcid.org/0000-0001-7764-3459"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Perttu Hamalainen","raw_affiliation_strings":["Aalto University, Helsinki, Finland","Aalto University Helsinki, Finland#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University Helsinki, Finland#TAB#","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058061575","display_name":"Amin Babadi","orcid":"https://orcid.org/0000-0003-4930-9917"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Amin Babadi","raw_affiliation_strings":["Aalto University, Helsinki, Finland","Aalto University Helsinki, Finland#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University Helsinki, Finland#TAB#","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667081","display_name":"Xiaoxiao Ma","orcid":"https://orcid.org/0009-0007-6289-6120"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xiaoxiao Ma","raw_affiliation_strings":["Aalto University, Helsinki, Finland","Aalto University Helsinki, Finland#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University Helsinki, Finland#TAB#","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103009697","display_name":"Jaakko Lehtinen","orcid":"https://orcid.org/0000-0001-9418-4944"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jaakko Lehtinen","raw_affiliation_strings":["NVIDIA","nVidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]},{"raw_affiliation_string":"nVidia","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5207,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.93893097,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"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/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":0.9860000014305115,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9821000099182129,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cma-es","display_name":"CMA-ES","score":0.904502272605896},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.678922176361084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6674900054931641},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6210975050926208},{"id":"https://openalex.org/keywords/optimization-algorithm","display_name":"Optimization algorithm","score":0.5512906312942505},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5481661558151245},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.542411208152771},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4869788587093353},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.47303053736686707},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.46146777272224426},{"id":"https://openalex.org/keywords/evolution-strategy","display_name":"Evolution strategy","score":0.4119231402873993},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.41124778985977173},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33628636598587036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30485230684280396},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.3001895546913147},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23394331336021423},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07665657997131348}],"concepts":[{"id":"https://openalex.org/C205555498","wikidata":"https://www.wikidata.org/wiki/Q505588","display_name":"CMA-ES","level":4,"score":0.904502272605896},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.678922176361084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6674900054931641},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6210975050926208},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.5512906312942505},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5481661558151245},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.542411208152771},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4869788587093353},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.47303053736686707},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.46146777272224426},{"id":"https://openalex.org/C207002847","wikidata":"https://www.wikidata.org/wiki/Q2912857","display_name":"Evolution strategy","level":3,"score":0.4119231402873993},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.41124778985977173},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33628636598587036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30485230684280396},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.3001895546913147},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23394331336021423},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07665657997131348},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/mlsp49062.2020.9231618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp49062.2020.9231618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.02541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.02541","pdf_url":"https://arxiv.org/pdf/1810.02541","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/101640","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/daec99e2-d5cd-4e96-90c5-a97bd9faa5b0","pdf_url":"https://research.aalto.fi/files/53205995/2020_ppocma.pdf","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},{"id":"mag:2895279298","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1810.02541","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1810.02541","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1810.02541","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.02541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.02541","pdf_url":"https://arxiv.org/pdf/1810.02541","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W102487131","https://openalex.org/W1191599655","https://openalex.org/W1540706608","https://openalex.org/W1771410628","https://openalex.org/W2101539915","https://openalex.org/W2104733512","https://openalex.org/W2132083787","https://openalex.org/W2220858814","https://openalex.org/W2336687883","https://openalex.org/W2616451375","https://openalex.org/W2736601468","https://openalex.org/W2785738552","https://openalex.org/W2796290181","https://openalex.org/W2885109541","https://openalex.org/W2887776484","https://openalex.org/W2902286283","https://openalex.org/W2963960193","https://openalex.org/W2978455699","https://openalex.org/W2987886924","https://openalex.org/W6638018090","https://openalex.org/W6675999342","https://openalex.org/W6754051069","https://openalex.org/W6772196467"],"related_works":["https://openalex.org/W2736601468","https://openalex.org/W2145339207","https://openalex.org/W1771410628","https://openalex.org/W2964043796","https://openalex.org/W2173248099","https://openalex.org/W2121863487","https://openalex.org/W2781726626","https://openalex.org/W2257979135","https://openalex.org/W1757796397","https://openalex.org/W2596367596","https://openalex.org/W2787938642","https://openalex.org/W2158782408","https://openalex.org/W2155968351","https://openalex.org/W2766447205","https://openalex.org/W2046033161","https://openalex.org/W1522301498","https://openalex.org/W3082609601","https://openalex.org/W2558698000","https://openalex.org/W2968150966","https://openalex.org/W2017973856"],"abstract_inverted_index":{"Proximal":[0],"Policy":[1],"Optimization":[2],"(PPO)":[3],"is":[4,105],"a":[5,18,50,64],"highly":[6],"popular":[7],"model-free":[8],"reinforcement":[9],"learning":[10],"(RL)":[11],"approach.":[12],"However,":[13],"we":[14,61],"observe":[15],"that":[16,69,99],"in":[17,43,58,90,119],"continuous":[19,92],"action":[20],"space,":[21],"PPO":[22],"can":[23],"prematurely":[24],"shrink":[25],"the":[26,37,72,110],"exploration":[27,73],"variance,":[28],"which":[29],"leads":[30],"to":[31,40,75,83,103,109,116],"slow":[32],"progress":[33],"and":[34],"may":[35],"make":[36],"algorithm":[38,86],"prone":[39],"getting":[41],"stuck":[42],"local":[44],"optima.":[45],"Drawing":[46],"inspiration":[47],"from":[48],"CMA-ES,":[49],"black-box":[51],"evolutionary":[52],"optimization":[53,67,122],"method":[54],"designed":[55],"for":[56],"robustness":[57],"similar":[59],"situations,":[60],"propose":[62],"PPO-CMA,":[63,100],"proximal":[65],"policy":[66],"approach":[68],"adaptively":[70],"expands":[71],"variance":[74],"speed":[76],"up":[77],"progress.":[78],"With":[79],"only":[80],"minor":[81],"changes":[82],"PPO,":[84,104],"our":[85],"considerably":[87],"improves":[88],"performance":[89],"Roboschool":[91],"control":[93],"benchmarks.":[94],"Our":[95],"results":[96],"also":[97],"show":[98],"as":[101],"opposed":[102],"significantly":[106],"less":[107],"sensitive":[108],"choice":[111],"of":[112],"hyperparameters,":[113],"allowing":[114],"one":[115],"use":[117],"it":[118],"complex":[120],"movement":[121],"tasks":[123],"without":[124],"requiring":[125],"tedious":[126],"tuning.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}