{"id":"https://openalex.org/W2119007372","doi":"https://doi.org/10.4249/scholarpedia.3698","title":"Policy gradient methods","display_name":"Policy gradient methods","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2119007372","doi":"https://doi.org/10.4249/scholarpedia.3698","mag":"2119007372"},"language":"en","primary_location":{"id":"doi:10.4249/scholarpedia.3698","doi":"https://doi.org/10.4249/scholarpedia.3698","is_oa":true,"landing_page_url":"https://doi.org/10.4249/scholarpedia.3698","pdf_url":null,"source":{"id":"https://openalex.org/S177062229","display_name":"Scholarpedia","issn_l":"1941-6016","issn":["1941-6016"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1"],"host_organization":"https://openalex.org/P4310316840","host_organization_name":"Scholarpedia Corporation","host_organization_lineage":["https://openalex.org/P4310316840"],"host_organization_lineage_names":["Scholarpedia Corporation"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scholarpedia","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.4249/scholarpedia.3698","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091","observed_orcids":["https://orcid.org/0000-0002-5266-8091"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"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":true,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society","institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071367253"],"corresponding_institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210135521"],"apc_list":null,"apc_paid":null,"fwci":0.8008,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.72807647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":"5","issue":"11","first_page":"3698","last_page":"3698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11195","display_name":"Simulation Techniques and Applications","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.9179999828338623},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8769999742507935},{"id":"https://openalex.org/keywords/policy-search","display_name":"policy search","score":0.7480000257492065},{"id":"https://openalex.org/keywords/expected-return-maximization","display_name":"expected return maximization","score":0.8370000123977661},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.7160000205039978},{"id":"https://openalex.org/keywords/continuous-state-action-spaces","display_name":"continuous state and action spaces","score":0.7279999852180481},{"id":"https://openalex.org/keywords/off-policy-learning","display_name":"off-policy learning","score":0.7620000243186951},{"id":"https://openalex.org/keywords/convergence-guarantees","display_name":"convergence guarantees","score":0.5490000247955322},{"id":"https://openalex.org/keywords/local-optimality","display_name":"local optimality","score":0.49000000953674316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3743204176425934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4249/scholarpedia.3698","doi":"https://doi.org/10.4249/scholarpedia.3698","is_oa":true,"landing_page_url":"https://doi.org/10.4249/scholarpedia.3698","pdf_url":null,"source":{"id":"https://openalex.org/S177062229","display_name":"Scholarpedia","issn_l":"1941-6016","issn":["1941-6016"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1"],"host_organization":"https://openalex.org/P4310316840","host_organization_name":"Scholarpedia Corporation","host_organization_lineage":["https://openalex.org/P4310316840"],"host_organization_lineage_names":["Scholarpedia Corporation"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scholarpedia","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.4249/scholarpedia.3698","doi":"https://doi.org/10.4249/scholarpedia.3698","is_oa":true,"landing_page_url":"https://doi.org/10.4249/scholarpedia.3698","pdf_url":null,"source":{"id":"https://openalex.org/S177062229","display_name":"Scholarpedia","issn_l":"1941-6016","issn":["1941-6016"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1"],"host_organization":"https://openalex.org/P4310316840","host_organization_name":"Scholarpedia Corporation","host_organization_lineage":["https://openalex.org/P4310316840"],"host_organization_lineage_names":["Scholarpedia Corporation"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scholarpedia","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W60181528","https://openalex.org/W1530191702","https://openalex.org/W2046765929","https://openalex.org/W2064076655","https://openalex.org/W2119717200","https://openalex.org/W2125612430","https://openalex.org/W2155027007"],"related_works":["https://openalex.org/W4250385743","https://openalex.org/W3032096424","https://openalex.org/W7171813712","https://openalex.org/W2112239212","https://openalex.org/W4387559814","https://openalex.org/W3039845099","https://openalex.org/W6977152758","https://openalex.org/W4402941410","https://openalex.org/W4405331267","https://openalex.org/W298976786"],"abstract_inverted_index":{"A":[0],"policy":[1,15,25,35,39,69,82,99],"gradient":[2,17,54],"method":[3],"is":[4],"a":[5,12,34,37,50,96],"reinforcement":[6],"learning":[7],"approach":[8],"that":[9,28,130],"directly":[10],"optimizes":[11],"parametrized":[13],"control":[14],"by":[16],"descent.":[18],"It":[19],"belongs":[20],"to":[21,91,93],"the":[22,30,61,68,80,84,117],"class":[23,40],"of":[24,33,64],"search":[26],"techniques":[27],"maximize":[29],"expected":[31],"return":[32],"in":[36,67,120,126],"fixed":[38],"while":[41],"traditional":[42],"value":[43,51,86],"function":[44],"approximation":[45],"approaches":[46,55],"derive":[47],"policies":[48],"from":[49],"function.":[52,87],"Policy":[53],"have":[56],"various":[57],"advantages:":[58],"they":[59],"allow":[60],"straightforward":[62],"incorporation":[63],"domain":[65],"knowledge":[66],"parametrization":[70],"and":[71,100,105,107,129],"often":[72,108],"significantly":[73],"fewer":[74],"parameters":[75],"are":[76,89,116,133],"needed":[77],"for":[78],"representing":[79],"optimal":[81,98],"than":[83],"corresponding":[85],"They":[88],"guaranteed":[90],"converge":[92],"at":[94],"least":[95],"locally":[97],"can":[101],"handle":[102],"continuous":[103],"states":[104],"action,":[106],"even":[109],"imperfect":[110],"state":[111],"information.":[112],"Their":[113],"major":[114],"drawbags":[115],"difficult":[118],"use":[119],"off-policy":[121],"settings,":[122],"their":[123],"slow":[124],"convergence":[125],"discrete":[127],"problems":[128],"global":[131],"optima":[132],"not":[134],"attained.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}