{"id":"https://openalex.org/W2918175465","doi":"https://doi.org/10.1007/s10994-019-05807-0","title":"Compatible natural gradient policy search","display_name":"Compatible natural gradient policy search","publication_year":2019,"publication_date":"2019-05-20","ids":{"openalex":"https://openalex.org/W2918175465","doi":"https://doi.org/10.1007/s10994-019-05807-0","mag":"2918175465"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-019-05807-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05807-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05807-0.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","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/s10994-019-05807-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017983137","display_name":"Joni Pajarinen","orcid":"https://orcid.org/0000-0003-4469-8191"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE","FI"],"is_corresponding":true,"raw_author_name":"Joni Pajarinen","raw_affiliation_strings":["Intelligent Autonomous Systems, TU Darmstadt, Darmstadt, Germany","Tampere University, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0003-4469-8191","affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems, TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002615655","display_name":"Hong Linh Thai","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hong Linh Thai","raw_affiliation_strings":["Intelligent Autonomous Systems, TU Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems, TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075701789","display_name":"Riad Akrour","orcid":"https://orcid.org/0000-0002-8735-6960"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Riad Akrour","raw_affiliation_strings":["Intelligent Autonomous Systems, TU Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems, TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Intelligent Autonomous Systems, TU Darmstadt, Darmstadt, Germany","MPI for Intelligent Systems, Tuebingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems, TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"MPI for Intelligent Systems, Tuebingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110467801","display_name":"Gerhard Neumann","orcid":"https://orcid.org/0000-0002-5483-4225"},"institutions":[{"id":"https://openalex.org/I51532219","display_name":"University of Lincoln","ror":"https://ror.org/03yeq9x20","country_code":"GB","type":"education","lineage":["https://openalex.org/I51532219"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gerhard Neumann","raw_affiliation_strings":["Lincoln Center for Autonomous Systems, University of Lincoln, Lincoln, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lincoln Center for Autonomous Systems, University of Lincoln, Lincoln, UK","institution_ids":["https://openalex.org/I51532219"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017983137"],"corresponding_institution_ids":["https://openalex.org/I166825849","https://openalex.org/I31512782"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":1.8784,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89220607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"108","issue":"8-9","first_page":"1443","last_page":"1466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996399998664856,"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/entropy","display_name":"Entropy (arrow of time)","score":0.5835142135620117},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5803360342979431},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.49899959564208984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4914652109146118},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.46413442492485046},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38072702288627625},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.33126571774482727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22445178031921387}],"concepts":[{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5835142135620117},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5803360342979431},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.49899959564208984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4914652109146118},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.46413442492485046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38072702288627625},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33126571774482727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22445178031921387},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10994-019-05807-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05807-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05807-0.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:eprints.lincoln.ac.uk:36283","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196275","display_name":"Lincoln Repository (University of Lincoln)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51532219","host_organization_name":"University of Lincoln","host_organization_lineage":["https://openalex.org/I51532219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:trepo.tuni.fi:10024/215271","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/215271","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:147236","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/147236/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Artikel"}],"best_oa_location":{"id":"doi:10.1007/s10994-019-05807-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05807-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05807-0.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G131961447","display_name":null,"funder_award_id":"640554","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G2437159836","display_name":null,"funder_award_id":"645582","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G2553111511","display_name":null,"funder_award_id":"PA 3179/1-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8367549587","display_name":null,"funder_award_id":"3179/1-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2918175465.pdf","grobid_xml":"https://content.openalex.org/works/W2918175465.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1533285455","https://openalex.org/W1564755532","https://openalex.org/W1577352482","https://openalex.org/W1731081199","https://openalex.org/W1970789124","https://openalex.org/W2111967991","https://openalex.org/W2112036188","https://openalex.org/W2119717200","https://openalex.org/W2130801532","https://openalex.org/W2144913588","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2165150801","https://openalex.org/W2166160300","https://openalex.org/W2167117957","https://openalex.org/W2172968643","https://openalex.org/W2173248099","https://openalex.org/W2185709919","https://openalex.org/W2296319761","https://openalex.org/W2342662072","https://openalex.org/W2473408367","https://openalex.org/W2597289420","https://openalex.org/W2613433911","https://openalex.org/W2749928749","https://openalex.org/W2767621168","https://openalex.org/W2785738552","https://openalex.org/W2811292668","https://openalex.org/W2892218381","https://openalex.org/W2949608212","https://openalex.org/W2952063594","https://openalex.org/W2963622280","https://openalex.org/W2964043796","https://openalex.org/W4250589301","https://openalex.org/W6633472939","https://openalex.org/W6638018090","https://openalex.org/W6653435097","https://openalex.org/W6676560026","https://openalex.org/W6679257226","https://openalex.org/W6684205842","https://openalex.org/W6745935785","https://openalex.org/W6747924173","https://openalex.org/W6748490488"],"related_works":["https://openalex.org/W2105321464","https://openalex.org/W2887774187","https://openalex.org/W2388220555","https://openalex.org/W1554844486","https://openalex.org/W1520875569","https://openalex.org/W3048739257","https://openalex.org/W1665563134","https://openalex.org/W2963604926","https://openalex.org/W2199957582","https://openalex.org/W2033178790"],"abstract_inverted_index":{"Trust-region":[0],"methods":[1],"have":[2],"yielded":[3],"state-of-the-art":[4,111],"results":[5,106,112],"in":[6,23,53,113,119],"policy":[7,27,51,74,92,97],"search.":[8],"A":[9],"common":[10],"approach":[11],"is":[12],"to":[13,16,76,81],"use":[14,43],"KL-divergence":[15],"bound":[17],"the":[18,32,44,70,73],"region":[19,37],"of":[20,47,72],"trust":[21,36],"resulting":[22],"a":[24,48,77,90],"natural":[25,33,45,65],"gradient":[26,34,66],"update.":[28],"We":[29],"show":[30,62,107],"that":[31,63,108],"and":[35,118],"optimization":[38],"are":[39],"equivalent":[40],"if":[41],"we":[42,61,88],"parameterization":[46],"standard":[49,64],"exponential":[50],"distribution":[52],"combination":[54],"with":[55],"compatible":[56,96],"value":[57],"function":[58],"approximation.":[59],"Moreover,":[60],"updates":[67],"may":[68],"reduce":[69],"entropy":[71,86,102],"according":[75],"wrong":[78],"schedule":[79],"leading":[80],"premature":[82],"convergence.":[83],"To":[84],"control":[85,116],"reduction":[87],"introduce":[89],"new":[91],"search":[93,98],"method":[94],"called":[95],"(COPOS)":[99],"which":[100],"bounds":[101],"loss.":[103],"The":[104],"experimental":[105],"COPOS":[109],"yields":[110],"challenging":[114],"continuous":[115],"tasks":[117],"discrete":[120],"partially":[121],"observable":[122],"tasks.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
