{"id":"https://openalex.org/W3169956959","doi":"https://doi.org/10.1109/icme51207.2021.9428188","title":"Ddper: Decentralized Distributed Prioritized Experience Replay","display_name":"Ddper: Decentralized Distributed Prioritized Experience Replay","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3169956959","doi":"https://doi.org/10.1109/icme51207.2021.9428188","mag":"3169956959"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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/A5030972033","display_name":"Sidun Liu","orcid":"https://orcid.org/0000-0001-7715-4698"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sidun Liu","raw_affiliation_strings":["National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,China","National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018873974","display_name":"Peng Qiao","orcid":"https://orcid.org/0000-0002-7882-6449"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Qiao","raw_affiliation_strings":["National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,China","National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051680867","display_name":"Yong Dou","orcid":"https://orcid.org/0000-0002-1256-8934"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Dou","raw_affiliation_strings":["National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,China","National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060842196","display_name":"Rongchun Li","orcid":"https://orcid.org/0000-0001-5922-7961"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongchun Li","raw_affiliation_strings":["National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,China","National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,National Laboratory for Parallel and Distributed Processing,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030972033"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52726615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"518","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9969000220298767,"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":0.9969000220298767,"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/T13219","display_name":"Mind wandering and attention","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.95169997215271,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.9202507734298706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8406455516815186},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7531194686889648},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.48388752341270447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3826380670070648},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.06350010633468628}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.9202507734298706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406455516815186},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7531194686889648},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.48388752341270447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3826380670070648},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.06350010633468628}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1658008008","https://openalex.org/W2064675550","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2168231600","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2781726626","https://openalex.org/W2786928559","https://openalex.org/W2788862220","https://openalex.org/W2805560727","https://openalex.org/W2908064123","https://openalex.org/W2951799221","https://openalex.org/W2964043796","https://openalex.org/W2995429865","https://openalex.org/W2996695841","https://openalex.org/W3013618273","https://openalex.org/W3034956653","https://openalex.org/W4287867830","https://openalex.org/W4297797010","https://openalex.org/W6636881020","https://openalex.org/W6677067356","https://openalex.org/W6684859321","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6744838376","https://openalex.org/W6747473740","https://openalex.org/W6748554570","https://openalex.org/W6748638692","https://openalex.org/W6748645729","https://openalex.org/W6751714826","https://openalex.org/W6757184387","https://openalex.org/W6769580333"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000"],"abstract_inverted_index":{"In":[0],"off-policy":[1,80],"reinforcement":[2],"learning,":[3],"prioritized":[4,14,29,58],"experience":[5,15,30,59],"replay":[6,16,31,52],"plays":[7],"an":[8],"important":[9],"role.":[10],"However,":[11],"the":[12,18,27,54,61,83,97,106,113,119,125],"centralized":[13,28],"becomes":[17],"bottleneck":[19],"for":[20],"efficient":[21],"training.":[22],"We":[23,75],"propose":[24],"to":[25],"approximate":[26],"in":[32,49,53],"a":[33,64,72,77,92],"distributed":[34],"and":[35,122,138],"decentralized":[36],"way":[37,56],"under":[38],"certain":[39,73],"mild":[40],"assumptions.":[41],"To":[42],"be":[43],"specific,":[44],"each":[45],"actor":[46],"stores":[47],"samples":[48,67],"its":[50],"local":[51],"same":[55,120],"as":[57,112],"replay,":[60],"learner":[62],"fetches":[63],"batch":[65],"of":[66,96,115],"from":[68],"these":[69],"replays":[70],"following":[71],"strategy.":[74],"implement":[76],"Deep":[78],"Q-Learning":[79],"algorithm":[81,121],"upon":[82],"proposed":[84,107,126],"framework.":[85],"The":[86,101],"comparison":[87],"experiments":[88],"are":[89],"performed":[90],"on":[91],"commonly":[93],"used":[94],"subset":[95],"Atari-57":[98],"learning":[99],"environment.":[100],"experimental":[102],"results":[103],"show":[104],"that":[105,134],"framework":[108,127],"speeds":[109],"up":[110],"training":[111],"number":[114],"actors":[116,130,141],"increases.":[117],"With":[118],"hyper-parameter":[123],"settings,":[124],"with":[128,136],"16":[129],"achieves":[131],"superior":[132],"performance":[133],"Ape-X":[135],"32":[137],"even":[139],"more":[140],"does.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}