{"id":"https://openalex.org/W2986409676","doi":"https://doi.org/10.1145/3356464.3357704","title":"An efficient reinforcement learning algorithm for learning deterministic policies in continuous domains","display_name":"An efficient reinforcement learning algorithm for learning deterministic policies in continuous domains","publication_year":2019,"publication_date":"2019-10-13","ids":{"openalex":"https://openalex.org/W2986409676","doi":"https://doi.org/10.1145/3356464.3357704","mag":"2986409676"},"language":"en","primary_location":{"id":"doi:10.1145/3356464.3357704","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3356464.3357704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Conference on Distributed Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028712584","display_name":"Matthieu Zimmer","orcid":"https://orcid.org/0000-0002-8029-308X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Matthieu Zimmer","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073106112","display_name":"Paul Weng","orcid":"https://orcid.org/0000-0002-2008-4569"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Paul Weng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14019679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9954000115394592,"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":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8689128160476685},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7595970630645752},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.7156765460968018},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.714466392993927},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5566184520721436},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.537497341632843},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5102543830871582},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4818619191646576},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.47059524059295654},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.423652708530426},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4190000891685486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3872146010398865},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32679975032806396},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3095574975013733},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13632485270500183},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08428171277046204}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8689128160476685},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7595970630645752},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.7156765460968018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.714466392993927},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5566184520721436},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.537497341632843},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5102543830871582},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4818619191646576},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.47059524059295654},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.423652708530426},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4190000891685486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3872146010398865},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32679975032806396},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3095574975013733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13632485270500183},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08428171277046204},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3356464.3357704","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3356464.3357704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Conference on Distributed Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1514587017","https://openalex.org/W2009303086","https://openalex.org/W2101539915","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2411690432","https://openalex.org/W2736601468","https://openalex.org/W2892113304","https://openalex.org/W2948414426","https://openalex.org/W2950492145","https://openalex.org/W2952967722","https://openalex.org/W2966754320"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2142189862","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,106],"present":[4],"an":[5,8,38],"improvement":[6],"to":[7],"existing":[9],"reinforcement":[10],"learning":[11],"algorithm":[12,111],"that":[13,108],"can":[14,31,112],"learn":[15],"very":[16],"efficiently":[17],"deterministic":[18],"policies":[19],"in":[20,53],"continuous":[21],"domains.":[22],"It":[23],"builds":[24],"on":[25,97,103],"two":[26,90],"recently-proposed":[27],"techniques.":[28],"First,":[29],"it":[30,58],"be":[32],"seen":[33],"as":[34],"a":[35,60],"variation":[36],"of":[37,67,79,93,125],"actor-critic":[39],"algorithm,":[40],"called":[41,71],"Penalized":[42],"Neural-Fitted":[43],"Actor":[44],"Critic":[45],"(PeNFAC)":[46],"[24],":[47],"which":[48],"showed":[49],"excellent":[50],"experimental":[51],"performance":[52],"the":[54,64,68,77,101,126],"Roboschool":[55,127],"environments.":[56],"Second,":[57],"incorporates":[59],"better":[61],"estimate":[62],"for":[63],"value":[65],"function":[66],"current":[69],"policy,":[70],"V-trace":[72],"target":[73],"[3],":[74],"by":[75,83],"allowing":[76],"reuse":[78],"off-policy":[80],"data":[81],"generated":[82],"recent":[84],"previous":[85],"policies.":[86],"We":[87],"experimentally":[88],"compare":[89],"different":[91],"implementations":[92],"V-trace:":[94],"one":[95],"based":[96],"n-step":[98],"returns":[99],"and":[100],"other":[102],"\u03bb-returns.":[104],"Finally,":[105],"show":[107],"our":[109],"proposed":[110],"outperform":[113],"several":[114],"state-of-the-art":[115],"algorithms":[116],"(TD3,":[117],"DDPG,":[118],"PPO,":[119],"PeNFAC,":[120],"NFAC)":[121],"over":[122],"three":[123],"environments":[124],"benchmark":[128],"(Hopper,":[129],"HalfCheetah,":[130],"Humanoid).":[131]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}