{"id":"https://openalex.org/W2769837327","doi":"https://doi.org/10.18420/in2017_214","title":"Training a deep policy gradient-based neural network with asynchronous learners on a simulated robotic problem","display_name":"Training a deep policy gradient-based neural network with asynchronous learners on a simulated robotic problem","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2769837327","doi":"https://doi.org/10.18420/in2017_214","mag":"2769837327"},"language":"en","primary_location":{"id":"doi:10.18420/in2017_214","is_oa":true,"landing_page_url":"https://doi.org/10.18420/in2017_214","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/in2017_214","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057579016","display_name":"Winfried L\u00f6tzsch","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"L\u00f6tzsch, Winfried","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016814228","display_name":"Julien Vitay","orcid":"https://orcid.org/0000-0001-5229-2349"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vitay, Julien","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089469300","display_name":"Fred H. Hamker","orcid":"https://orcid.org/0000-0001-9104-7143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hamker, Fred","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057579016"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15885731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2143","last_page":"2154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.6273000240325928,"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/T10320","display_name":"Neural Networks and Applications","score":0.6273000240325928,"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/T14470","display_name":"Advanced Data Processing Techniques","score":0.612500011920929,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.6013000011444092,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7387732267379761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6921606063842773},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6547433733940125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6463431119918823},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.563922107219696},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4423944056034088},{"id":"https://openalex.org/keywords/asynchronous-learning","display_name":"Asynchronous learning","score":0.4187226891517639},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34928905963897705},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23582983016967773},{"id":"https://openalex.org/keywords/teaching-method","display_name":"Teaching method","score":0.12293368577957153},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.11597970128059387},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10509124398231506}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7387732267379761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6921606063842773},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6547433733940125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6463431119918823},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.563922107219696},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4423944056034088},{"id":"https://openalex.org/C2777072894","wikidata":"https://www.wikidata.org/wiki/Q4812204","display_name":"Asynchronous learning","level":5,"score":0.4187226891517639},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34928905963897705},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23582983016967773},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"score":0.12293368577957153},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.11597970128059387},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10509124398231506},{"id":"https://openalex.org/C19122763","wikidata":"https://www.wikidata.org/wiki/Q7662215","display_name":"Synchronous learning","level":4,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18420/in2017_214","is_oa":true,"landing_page_url":"https://doi.org/10.18420/in2017_214","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2769837327","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/gi/gi2017.html#LotzschVH17","pdf_url":null,"source":{"id":"https://openalex.org/S4306511462","display_name":"GI-Jahrestagung","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"GI-Jahrestagung","raw_type":null}],"best_oa_location":{"id":"doi:10.18420/in2017_214","is_oa":true,"landing_page_url":"https://doi.org/10.18420/in2017_214","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2964043796","https://openalex.org/W3100789280","https://openalex.org/W3162902697","https://openalex.org/W3185108905","https://openalex.org/W3039502116","https://openalex.org/W3101253939","https://openalex.org/W2922485250","https://openalex.org/W2921555828","https://openalex.org/W2939023475","https://openalex.org/W2166575060","https://openalex.org/W2223493585","https://openalex.org/W2610686804","https://openalex.org/W3123364362","https://openalex.org/W2806832624","https://openalex.org/W1980620643","https://openalex.org/W2965867197","https://openalex.org/W3131815131","https://openalex.org/W2527045502","https://openalex.org/W2964180249","https://openalex.org/W2171128163"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,112],"deep":[3,40,75],"reinforcement":[4],"learning":[5,146],"methods":[6,36],"have":[7],"attracted":[8],"a":[9,57,115,149],"lot":[10],"of":[11,14,28,103,136,143],"attention,":[12],"because":[13],"their":[15,90],"ability":[16],"to":[17,80,105,123,159],"use":[18],"raw":[19],"signals":[20],"such":[21,69],"as":[22,25,70,98],"video":[23],"streams":[24],"inputs,":[26],"instead":[27],"pre-processed":[29],"state":[30],"variables.":[31],"However,":[32],"the":[33,48,63,133,141],"most":[34],"popular":[35],"(value-based":[37],"methods,":[38,68],"e.g.":[39],"Q-networks)":[41],"focus":[42],"on":[43,148],"discrete":[44,126],"action":[45,59,87],"spaces":[46],"(e.g.":[47],"left/right":[49],"buttons),":[50],"while":[51],"realistic":[52,161],"robotic":[53,137,153],"applications":[54,158],"usually":[55],"require":[56],"continuous":[58,86,134],"space":[60],"(for":[61],"example":[62],"joint":[64],"space).":[65],"Policy":[66],"gradient":[67,73],"stochastic":[71],"policy":[72,77],"or":[74],"deterministic":[76],"gradient,":[78],"propose":[79],"overcome":[81],"this":[82,108,144],"problem":[83],"by":[84],"allowing":[85],"spaces.":[88],"Despite":[89],"promises,":[91],"they":[92,99],"suffer":[93],"from":[94],"long":[95],"training":[96],"times":[97],"need":[100],"huge":[101],"numbers":[102],"interactions":[104],"converge.":[106],"In":[107],"paper,":[109],"we":[110],"investigate":[111],"how":[113],"far":[114],"recent":[116],"asynchronously":[117],"parallel":[118],"actor-critic":[119],"approach,":[120],"initially":[121],"proposed":[122],"speed":[124],"up":[125],"RL":[127],"algorithms,":[128],"could":[129],"be":[130],"used":[131],"for":[132],"control":[135],"arms.":[138],"We":[139],"demonstrate":[140],"capabilities":[142],"end-to-end":[145],"algorithm":[147],"simulated":[150],"2":[151],"degrees-of-freedom":[152],"arm":[154],"and":[155],"discuss":[156],"its":[157],"more":[160],"scenarios.":[162]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}