{"id":"https://openalex.org/W3090109306","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207008","title":"Latent Context Based Soft Actor-Critic","display_name":"Latent Context Based Soft Actor-Critic","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090109306","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207008","mag":"3090109306"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5101848345","display_name":"Yuan Pu","orcid":"https://orcid.org/0000-0002-1322-5642"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuan Pu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038630321","display_name":"Shaochen Wang","orcid":"https://orcid.org/0000-0002-6985-240X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaochen Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100635494","display_name":"Xin Yao","orcid":"https://orcid.org/0000-0001-8837-4442"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365157","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-2332-3959"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101848345"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63554062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"518","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":0.9959999918937683,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9800999760627747,"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/computer-science","display_name":"Computer science","score":0.8340665102005005},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.742480456829071},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7000514268875122},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6712462902069092},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6049859523773193},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.5602791905403137},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5592201948165894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5473818182945251},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5444208383560181},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5210751295089722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8340665102005005},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.742480456829071},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7000514268875122},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6712462902069092},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6049859523773193},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.5602791905403137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5592201948165894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5473818182945251},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5444208383560181},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5210751295089722},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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:10.1109/ijcnn48605.2020.9207008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W64088143","https://openalex.org/W1522301498","https://openalex.org/W1585603966","https://openalex.org/W1662842982","https://openalex.org/W1986014385","https://openalex.org/W2061562262","https://openalex.org/W2097381042","https://openalex.org/W2121092017","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2291973609","https://openalex.org/W2604763608","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2785342287","https://openalex.org/W2788904251","https://openalex.org/W2908064123","https://openalex.org/W2923504512","https://openalex.org/W2952526277","https://openalex.org/W2962937519","https://openalex.org/W2962938178","https://openalex.org/W2963176272","https://openalex.org/W2963864421","https://openalex.org/W2964078140","https://openalex.org/W2964121744","https://openalex.org/W4300514939","https://openalex.org/W6631190155","https://openalex.org/W6635049011","https://openalex.org/W6674600207","https://openalex.org/W6677939520","https://openalex.org/W6684921986","https://openalex.org/W6696783566","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748566876","https://openalex.org/W6748600884","https://openalex.org/W6751959828","https://openalex.org/W6757184387","https://openalex.org/W6760698134","https://openalex.org/W6761908843","https://openalex.org/W6780559895","https://openalex.org/W6903351479"],"related_works":["https://openalex.org/W2461917396","https://openalex.org/W2037497866","https://openalex.org/W4243467573","https://openalex.org/W1502435251","https://openalex.org/W62001224","https://openalex.org/W3032390039","https://openalex.org/W1584341211","https://openalex.org/W3122667150","https://openalex.org/W4393387622","https://openalex.org/W3145681568"],"abstract_inverted_index":{"The":[0,53],"performance":[1,93,141],"of":[2,70,99,133,146],"deep":[3],"reinforcement":[4],"learning":[5],"methods":[6],"prone":[7],"to":[8,12,49,58,78,123,129],"degenerate":[9],"when":[10],"applied":[11],"tasks":[13,109],"requiring":[14],"relatively":[15],"longer":[16],"horizon":[17],"memory":[18],"or":[19],"with":[20,94,110,126,142,148],"highly":[21],"variable":[22],"dynamics.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27,115],"utilize":[28],"the":[29,41,63,68,71],"probabilistic":[30],"latent":[31,54],"context":[32,55],"variables":[33],"motivated":[34],"by":[35],"recent":[36],"Meta-RL":[37],"materials,":[38],"and":[39,67,103,137],"propose":[40],"Latent":[42],"Context":[43],"based":[44],"Soft":[45],"Actor-Critic":[46],"(LC-SAC)":[47],"approach":[48],"address":[50],"aforementioned":[51],"issues.":[52],"is":[56],"capable":[57],"encode":[59],"information":[60],"about":[61],"both":[62],"agent's":[64],"previous":[65],"behaviors":[66],"dynamics":[69],"current":[72],"undergoing":[73],"environment,":[74],"which":[75],"empirically":[76],"believed":[77],"be":[79],"beneficial":[80],"for":[81],"efficient":[82,131],"policy":[83],"optimization.":[84],"Experiment":[85],"results":[86],"demonstrate":[87],"that":[88],"LC-SAC":[89,125],"can":[90],"achieve":[91,139],"comparable":[92],"SAC":[95,105],"on":[96],"a":[97,118],"collection":[98],"continuous":[100],"control":[101],"benchmarks":[102],"outperforms":[104],"in":[106],"some":[107],"particular":[108],"above":[111],"two":[112],"characteristics.":[113],"Moreover,":[114],"also":[116],"introduce":[117],"simple":[119],"but":[120],"general":[121],"procedure":[122],"integrate":[124],"diverse-quality":[127],"demonstrations":[128],"enable":[130],"reuse":[132],"human":[134],"prior":[135],"knowledge,":[136],"finally":[138],"competitive":[140],"comparatively":[143],"small":[144],"number":[145],"interactions":[147],"environments.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}