{"id":"https://openalex.org/W2684685482","doi":"https://doi.org/10.1609/aaai.v32i1.11607","title":"Expected Policy Gradients","display_name":"Expected Policy Gradients","publication_year":2018,"publication_date":"2018-04-29","ids":{"openalex":"https://openalex.org/W2684685482","doi":"https://doi.org/10.1609/aaai.v32i1.11607","mag":"2684685482"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v32i1.11607","doi":"https://doi.org/10.1609/aaai.v32i1.11607","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v32i1.11607","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v32i1.11607","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043239539","display_name":"Kamil Ciosek","orcid":"https://orcid.org/0000-0002-0238-9393","observed_orcids":["https://orcid.org/0000-0002-0238-9393"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kamil Ciosek","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056879203","display_name":"Shimon Whiteson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shimon Whiteson","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.7086,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.75353107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"32","issue":"1","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":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/deterministic-policy-gradient","display_name":"deterministic policy gradient","score":0.996999979019165},{"id":"https://openalex.org/keywords/policy-gradient-theorem","display_name":"policy gradient theorem","score":0.9039999842643738},{"id":"https://openalex.org/keywords/gradient-variance-reduction","display_name":"gradient variance reduction","score":0.9190000295639038},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.5740000009536743},{"id":"https://openalex.org/keywords/mujoco","display_name":"MuJoCo","score":0.6190000176429749}],"concepts":[{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.813660740852356},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.6516629457473755},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5968834161758423},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5913884043693542},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5490185022354126},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5125486850738525},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5091602206230164},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.506332516670227},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.49587926268577576},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.49313896894454956},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4857907295227051},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4657849371433258},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4177861511707306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39766496419906616},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13360199332237244},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1322002112865448},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1317504346370697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12759336829185486},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07621046900749207},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"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:10.1609/aaai.v32i1.11607","doi":"https://doi.org/10.1609/aaai.v32i1.11607","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v32i1.11607","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1706.05374","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.05374","pdf_url":"https://arxiv.org/pdf/1706.05374","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"mag:2684685482","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1706.05374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.1706.05374","doi":"https://doi.org/10.48550/arxiv.1706.05374","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1706.05374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v32i1.11607","doi":"https://doi.org/10.1609/aaai.v32i1.11607","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v32i1.11607","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4138839253","display_name":"Coevolutionary Policy Search","funder_award_id":"637713","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"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/W2684685482.pdf","grobid_xml":"https://content.openalex.org/works/W2684685482.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1646707810","https://openalex.org/W1771410628","https://openalex.org/W1906772730","https://openalex.org/W2017957151","https://openalex.org/W2100752967","https://openalex.org/W2112964839","https://openalex.org/W2115126871","https://openalex.org/W2124175081","https://openalex.org/W2125612430","https://openalex.org/W2127107099","https://openalex.org/W2130005627","https://openalex.org/W2130801532","https://openalex.org/W2136602922","https://openalex.org/W2137104525","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2165150801","https://openalex.org/W2172968643","https://openalex.org/W2173248099","https://openalex.org/W2290354866","https://openalex.org/W2535247013","https://openalex.org/W2554984891","https://openalex.org/W2565081646","https://openalex.org/W2747402019","https://openalex.org/W2949608212","https://openalex.org/W2964121744","https://openalex.org/W3037207827","https://openalex.org/W3139377883","https://openalex.org/W6677049199"],"related_works":["https://openalex.org/W3027501728","https://openalex.org/W4402941439","https://openalex.org/W2116383462","https://openalex.org/W2133224499","https://openalex.org/W2964325153","https://openalex.org/W6891340489","https://openalex.org/W7139760764","https://openalex.org/W7139816810","https://openalex.org/W1596364083","https://openalex.org/W4380091059"],"abstract_inverted_index":{"We":[0,44,64,127],"propose":[1],"expected":[2,22],"policy":[3,9,14,49,58,105],"gradients":[4,10,15],"(EPG),":[5],"which":[6,53],"unify":[7],"stochastic":[8,55],"(SPG)":[11],"and":[12,56],"deterministic":[13,57,78],"(DPG)":[16],"for":[17,81],"reinforcement":[18],"learning.":[19],"Inspired":[20],"by":[21],"sarsa,":[23],"EPG":[24,68],"integrates":[25],"across":[26],"the":[27,31,38,41,54,70,73,82,108,113,116,120,125,142],"action":[28,39],"when":[29],"estimating":[30],"gradient,":[32],"instead":[33],"of":[34,52,72,115,119,136],"relying":[35],"only":[36],"on":[37],"in":[40,96,145],"sampled":[42],"trajectory.":[43],"establish":[45],"a":[46,97,103],"new":[47,134],"general":[48],"gradient":[50,59,74],"theorem,":[51],"theorems":[60],"are":[61],"special":[62],"cases.":[63],"also":[65],"prove":[66],"that":[67,92,107,132],"reduces":[69],"variance":[71],"estimates":[75],"without":[76],"requiring":[77],"policies":[79],"and,":[80],"Gaussian":[83,104],"case,":[84],"with":[85,102,122,141],"no":[86],"computational":[87],"overhead.":[88],"Finally,":[89],"we":[90],"show":[91],"it":[93],"is":[94,110],"optimal":[95],"certain":[98],"sense":[99],"to":[100,112,124],"explore":[101],"such":[106],"covariance":[109],"proportional":[111],"exponential":[114],"scaled":[117],"Hessian":[118],"critic":[121],"respect":[123],"actions.":[126],"present":[128],"empirical":[129],"results":[130],"confirming":[131],"this":[133],"form":[135],"exploration":[137],"substantially":[138],"outperforms":[139],"DPG":[140],"Ornstein-Uhlenbeck":[143],"heuristic":[144],"four":[146],"challenging":[147],"MuJoCo":[148],"domains.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2017-06-30T00:00:00"}