{"id":"https://openalex.org/W1890963104","doi":"https://doi.org/10.48550/arxiv.1508.04186","title":"Distributed Deep Q-Learning","display_name":"Distributed Deep Q-Learning","publication_year":2015,"publication_date":"2015-08-18","ids":{"openalex":"https://openalex.org/W1890963104","doi":"https://doi.org/10.48550/arxiv.1508.04186","mag":"1890963104"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1508.04186","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1508.04186","pdf_url":"https://arxiv.org/pdf/1508.04186","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1508.04186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050270415","display_name":"Hao Yi Ong","orcid":"https://orcid.org/0000-0002-6835-2745","observed_orcids":["https://orcid.org/0000-0002-6835-2745"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ong, Hao Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019313214","display_name":"Kevin Chavez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chavez, Kevin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067352367","display_name":"Augustus Hong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong, Augustus","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":85,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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/T11574","display_name":"Artificial Intelligence in Games","score":9.999999747378752e-05,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/deep-q-network","display_name":"deep Q-network","score":0.9729999899864197},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7250000238418579},{"id":"https://openalex.org/keywords/value-function-estimation","display_name":"value function estimation","score":0.8119999766349792},{"id":"https://openalex.org/keywords/game-agents","display_name":"game-playing agents","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4752090871334076},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4477420747280121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4329681098461151}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1508.04186","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1508.04186","pdf_url":"https://arxiv.org/pdf/1508.04186","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":"doi:10.48550/arxiv.1508.04186","doi":"https://doi.org/10.48550/arxiv.1508.04186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1508.04186","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":"pmh:oai:arXiv.org:1508.04186","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1508.04186","pdf_url":"https://arxiv.org/pdf/1508.04186","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1890963104.pdf","grobid_xml":"https://content.openalex.org/works/W1890963104.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1600046456","https://openalex.org/W1652505363","https://openalex.org/W1658008008","https://openalex.org/W1757796397","https://openalex.org/W2029949252","https://openalex.org/W2048226872","https://openalex.org/W2099397840","https://openalex.org/W2101355568","https://openalex.org/W2102017903","https://openalex.org/W2112796928","https://openalex.org/W2118858186","https://openalex.org/W2127412976","https://openalex.org/W2139418546","https://openalex.org/W2145339207","https://openalex.org/W2155893237","https://openalex.org/W2168231600","https://openalex.org/W2546302380","https://openalex.org/W2787259794","https://openalex.org/W7098642242"],"related_works":["https://openalex.org/W1757796397","https://openalex.org/W1658008008","https://openalex.org/W2891764815","https://openalex.org/W2900747781","https://openalex.org/W4389230912","https://openalex.org/W7214828265","https://openalex.org/W3210957687","https://openalex.org/W2788325326","https://openalex.org/W2804155543","https://openalex.org/W2986251207"],"abstract_inverted_index":{"We":[0,98],"propose":[1],"a":[2,28,34,47,58,83,122],"distributed":[3],"deep":[4,26,64,102],"learning":[5,80],"model":[6,21],"to":[7,73,117],"successfully":[8],"learn":[9],"control":[10],"policies":[11],"directly":[12],"from":[13,53],"high-dimensional":[14],"sensory":[15],"input":[16,39],"using":[17],"reinforcement":[18,79],"learning.":[19],"The":[20],"is":[22,40,46,87],"based":[23],"on":[24,121],"the":[25,63,69,74,85,94,101,107,110],"Q-network,":[27],"convolutional":[29],"neural":[30],"network":[31],"trained":[32],"with":[33,93,125],"variant":[35],"of":[36,76,96],"Q-learning.":[37],"Its":[38],"raw":[41],"pixels":[42,108],"and":[43,90,109],"its":[44],"output":[45],"value":[48],"function":[49],"estimating":[50],"future":[51],"rewards":[52],"taking":[54],"an":[55],"action":[56],"given":[57],"system":[59],"state.":[60],"To":[61],"distribute":[62],"Q-network":[65,103],"training,":[66],"we":[67],"adapt":[68],"DistBelief":[70],"software":[71],"framework":[72],"context":[75],"efficiently":[77],"training":[78],"agents.":[81],"As":[82],"result,":[84],"method":[86],"completely":[88],"asynchronous":[89],"scales":[91],"well":[92],"number":[95],"machines.":[97],"demonstrate":[99],"that":[100],"agent,":[104],"receiving":[105],"only":[106],"game":[111,124],"score":[112],"as":[113],"inputs,":[114],"was":[115],"able":[116],"achieve":[118],"reasonable":[119],"success":[120],"simple":[123],"minimal":[126],"parameter":[127],"tuning.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}