{"id":"https://openalex.org/W4379364922","doi":"https://doi.org/10.1145/3583788.3583802","title":"Joint Action Representation and Prioritized Experience Replay for Reinforcement Learning in Large Discrete Action Spaces","display_name":"Joint Action Representation and Prioritized Experience Replay for Reinforcement Learning in Large Discrete Action Spaces","publication_year":2023,"publication_date":"2023-01-05","ids":{"openalex":"https://openalex.org/W4379364922","doi":"https://doi.org/10.1145/3583788.3583802"},"language":"en","primary_location":{"id":"doi:10.1145/3583788.3583802","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3583788.3583802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 The 7th International Conference on Machine Learning and Soft Computing (ICMLSC)","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/A5052592014","display_name":"Xueyu Wei","orcid":"https://orcid.org/0000-0003-0109-3360"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xueyu Wei","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University of Technology, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728738","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0002-0082-462X"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University of Technology, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101671767","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0001-9799-4635"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University of Technology, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081176072","display_name":"Yuanxia Shen","orcid":"https://orcid.org/0000-0003-1184-1270"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanxia Shen","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University of Technology, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005662290","display_name":"Gaohang Yu","orcid":"https://orcid.org/0000-0002-1546-3951"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaohang Yu","raw_affiliation_strings":["School of Science, Hangzhou Dianzi University, China"],"affiliations":[{"raw_affiliation_string":"School of Science, Hangzhou Dianzi University, China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052592014"],"corresponding_institution_ids":["https://openalex.org/I92178344"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0540927,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"101"},"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/T10603","display_name":"Smart Grid Energy Management","score":0.9860000014305115,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9562000036239624,"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/action","display_name":"Action (physics)","score":0.7113958597183228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7036781311035156},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6930426359176636},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6319841146469116},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5799204111099243},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.526991069316864},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4871668517589569},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4802730083465576},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4378596544265747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42313677072525024},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4176012873649597},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.41192591190338135},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34291958808898926},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3251732587814331},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2727307081222534},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12614557147026062}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7113958597183228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7036781311035156},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6930426359176636},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6319841146469116},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5799204111099243},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.526991069316864},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4871668517589569},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4802730083465576},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4378596544265747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42313677072525024},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4176012873649597},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.41192591190338135},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34291958808898926},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3251732587814331},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2727307081222534},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12614557147026062},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583788.3583802","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3583788.3583802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 The 7th International Conference on Machine Learning and Soft Computing (ICMLSC)","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":11,"referenced_works":["https://openalex.org/W2046376809","https://openalex.org/W2119567691","https://openalex.org/W3012066402","https://openalex.org/W3185784178","https://openalex.org/W4225288501","https://openalex.org/W4302039983","https://openalex.org/W4391725268","https://openalex.org/W6600472697","https://openalex.org/W6603690916","https://openalex.org/W6629502358","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W408992594"],"abstract_inverted_index":{"In":[0,27,107],"dealing":[1,168],"with":[2,79,169],"the":[3,28,33,39,42,53,68,73,80,86,97,104,108,112,123,127,132,148,159,164,170],"large":[4,171],"discrete":[5,172],"action":[6,10,44,49,75,173],"spaces,":[7],"a":[8,47,91,142],"joint":[9],"representation":[11],"and":[12,51,61,139,161],"prioritized":[13],"experience":[14,129],"replay":[15,105],"method":[16,36,145,166],"is":[17,56],"proposed":[18,165],"in":[19,85,103,167],"this":[20,63],"paper,":[21],"which":[22],"consists":[23],"of":[24,41,114,135,163],"three":[25],"modules.":[26],"first":[29],"module,":[30,88,110],"we":[31,89,121],"use":[32,140],"k-nearest":[34],"neighbor":[35],"to":[37,58,66,95,126,146],"reduce":[38,96],"dimensionality":[40],"original":[43],"space,":[45,50],"generating":[46],"compact":[48,64],"then":[52],"critic":[54],"network":[55],"introduced":[57],"further":[59],"evaluate":[60],"filter":[62],"space":[65],"obtain":[67],"optimal":[69,74],"action.":[70,83],"Note":[71],"that":[72],"may":[76],"have":[77],"inconsistency":[78],"actual":[81],"desired":[82],"Then":[84],"second":[87],"introduce":[90],"multi-step":[92],"update":[93],"technique":[94],"training":[98],"variance":[99],"when":[100,118],"storing":[101],"data":[102],"buffer.":[106],"third":[109],"considering":[111],"existence":[113],"correlation":[115],"between":[116],"samples":[117,149],"sampling":[119,144],"data,":[120],"assign":[122],"corresponding":[124],"weight":[125],"sample":[128],"by":[130],"calculating":[131],"absolute":[133],"value":[134],"temporal":[136],"difference":[137],"error":[138],"such":[141],"non-uniform":[143],"prioritize":[147],"for":[150],"sampling.":[151],"Experimental":[152],"results":[153],"on":[154],"four":[155],"benchmark":[156],"environments":[157],"demonstrate":[158],"effectiveness":[160],"efficiency":[162],"spaces.":[174]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}