{"id":"https://openalex.org/W3125245937","doi":"https://doi.org/10.1007/978-3-030-67537-0_21","title":"Distributed Reinforcement Learning with States Feature Encoding and States Stacking in Continuous Action Space","display_name":"Distributed Reinforcement Learning with States Feature Encoding and States Stacking in Continuous Action Space","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3125245937","doi":"https://doi.org/10.1007/978-3-030-67537-0_21","mag":"3125245937"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-67537-0_21","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-67537-0_21","pdf_url":null,"source":{"id":"https://openalex.org/S4393917809","display_name":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","issn_l":"1867-8211","issn":["1867-8211","1867-822X"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","raw_type":"book-chapter"},"type":"conference-paper","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/A5033759488","display_name":"Tianqi Xu","orcid":"https://orcid.org/0000-0002-9817-7597"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianqi Xu","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019758816","display_name":"Dianxi Shi","orcid":"https://orcid.org/0000-0002-8112-371X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dianxi Shi","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China","Tianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462292","display_name":"Zhiyuan Wang","orcid":"https://orcid.org/0000-0002-5990-9193"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Wang","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031813784","display_name":"Xucan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xucan Chen","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100677019","display_name":"Yaowen Zhang","orcid":"https://orcid.org/0000-0002-1379-2639"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaowen Zhang","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"340","last_page":"353"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9918000102043152,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8853294849395752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423635721206665},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6297481060028076},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4539605379104614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45339563488960266},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43276605010032654},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.4191691279411316},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41637110710144043},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4152721166610718},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3902713656425476},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09122663736343384}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8853294849395752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423635721206665},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6297481060028076},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4539605379104614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45339563488960266},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43276605010032654},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.4191691279411316},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41637110710144043},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4152721166610718},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3902713656425476},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09122663736343384},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-67537-0_21","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-67537-0_21","pdf_url":null,"source":{"id":"https://openalex.org/S4393917809","display_name":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","issn_l":"1867-8211","issn":["1867-8211","1867-822X"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W80219033","https://openalex.org/W2107726111","https://openalex.org/W2119567691","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2554952599","https://openalex.org/W2749807327","https://openalex.org/W2766447205","https://openalex.org/W2786036274","https://openalex.org/W2798705390","https://openalex.org/W2950395671","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964081807"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}