{"id":"https://openalex.org/W4205451831","doi":"https://doi.org/10.1145/3501409.3501550","title":"Concatenated Dynamic Reinforcement Learning for Multi-staged Tasks (MST)","display_name":"Concatenated Dynamic Reinforcement Learning for Multi-staged Tasks (MST)","publication_year":2021,"publication_date":"2021-10-22","ids":{"openalex":"https://openalex.org/W4205451831","doi":"https://doi.org/10.1145/3501409.3501550"},"language":"en","primary_location":{"id":"doi:10.1145/3501409.3501550","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3501409.3501550","pdf_url":null,"source":{"id":"https://openalex.org/S4363608789","display_name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","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/A5052441751","display_name":"Yendo Hu","orcid":"https://orcid.org/0000-0002-1638-9642"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yendo Hu","raw_affiliation_strings":["College of Ocean Information Engineering, Jimei University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"College of Ocean Information Engineering, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102974636","display_name":"Xue Bai","orcid":"https://orcid.org/0000-0002-8838-2167"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Bai","raw_affiliation_strings":["College of Ocean Information Engineering, Jimei University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"College of Ocean Information Engineering, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101747320","display_name":"Weijie Yang","orcid":"https://orcid.org/0000-0002-4725-7685"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijie Yang","raw_affiliation_strings":["College of Ocean Information Engineering, Jimei University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"College of Ocean Information Engineering, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045283922","display_name":"Yiliang Wu","orcid":"https://orcid.org/0000-0002-6067-6147"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiliang Wu","raw_affiliation_strings":["College of Ocean Information Engineering, Jimei University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"College of Ocean Information Engineering, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052441751"],"corresponding_institution_ids":["https://openalex.org/I161346416"],"apc_list":null,"apc_paid":null,"fwci":0.2513,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51832118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"781","last_page":"788"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9833999872207642,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9668999910354614,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8667265176773071},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7586426734924316},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7467088103294373},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6350736618041992},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6273490190505981},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5838844776153564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5546548962593079},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5432946681976318},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4882981777191162},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4461390972137451},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.4147699177265167},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33455079793930054},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09584268927574158}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8667265176773071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7586426734924316},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7467088103294373},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6350736618041992},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6273490190505981},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5838844776153564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5546548962593079},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5432946681976318},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4882981777191162},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4461390972137451},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.4147699177265167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33455079793930054},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09584268927574158},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3501409.3501550","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3501409.3501550","pdf_url":null,"source":{"id":"https://openalex.org/S4363608789","display_name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","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":16,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2081797037","https://openalex.org/W2145339207","https://openalex.org/W2156737235","https://openalex.org/W2162447456","https://openalex.org/W2173248099","https://openalex.org/W2260756217","https://openalex.org/W2604763608","https://openalex.org/W2973184394","https://openalex.org/W2994721849","https://openalex.org/W3033867302","https://openalex.org/W3088571672","https://openalex.org/W3118955349","https://openalex.org/W3139866229","https://openalex.org/W4405331568","https://openalex.org/W6637967152"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2937181779"],"abstract_inverted_index":{"There":[0],"exists":[1],"a":[2,35,59,63,67,76,146],"class":[3,19],"of":[4,20,54,69,84,95,102,116,131,149],"complex":[5,21,64,100,126],"tasks":[6,16],"that":[7,37,138,152],"can":[8,26],"be":[9,28,155],"distinctly":[10],"separated":[11],"into":[12],"multiple":[13,31],"concatenated":[14],"simpler":[15],"[1-2].":[17],"This":[18,48],"and":[22,34,71,93,107,118,175],"continuous":[23],"motion":[24,32],"processes":[25],"then":[27,72],"considered":[29],"as":[30],"sub-processes,":[33],"switch":[36],"brings":[38],"these":[39],"sub-processes":[40],"together":[41],"in":[42,167],"accordance":[43],"to":[44,61,110,123],"an":[45],"input":[46,169],"function.":[47],"paper":[49,89],"validates":[50],"the":[51,79,88,91,104,125,129,139,143],"potential":[52],"value":[53,94],"this":[55,96],"approach":[56,141],"by":[57,157],"proposing":[58],"method":[60],"train":[62],"task":[65,83,101,127],"through":[66,75],"series":[68],"sub-tasks,":[70],"concatenating":[73],"them":[74],"switch.":[77],"Through":[78],"classic":[80],"simulation":[81],"physical":[82],"OpenAI":[85],"Gym[3]:":[86],"cartpole,":[87],"demonstrates":[90],"viability":[92],"approach.":[97],"An":[98],"example":[99],"moving":[103],"pendulum":[105],"back":[106],"forth":[108],"between":[109],"points":[111],"was":[112],"used.":[113],"A":[114],"set":[115],"reward":[117],"switching":[119],"functions":[120],"were":[121],"developed":[122],"achieve":[124],"though":[128],"use":[130],"Deep":[132],"Q-network":[133],"(DQN)":[134],"[4].":[135],"Results":[136],"show":[137],"proposed":[140],"achieves":[142],"goal":[144],"within":[145],"limited":[147],"number":[148],"training":[150,178],"cycles":[151],"otherwise":[153],"cannot":[154],"met":[156],"other":[158],"traditional":[159],"means.":[160],"Alternative":[161],"reinforcement":[162],"learning":[163,173],"methods":[164],"would":[165],"result":[166],"more":[168],"parameters,":[170],"larger":[171,176],"deep":[172],"networks,":[174],"accumulative":[177],"cycles.":[179]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}