{"id":"https://openalex.org/W4312199098","doi":"https://doi.org/10.1109/scems56272.2022.9990639","title":"Trajectory optimization using dynamic programming and Q-learning","display_name":"Trajectory optimization using dynamic programming and Q-learning","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4312199098","doi":"https://doi.org/10.1109/scems56272.2022.9990639"},"language":"en","primary_location":{"id":"doi:10.1109/scems56272.2022.9990639","doi":"https://doi.org/10.1109/scems56272.2022.9990639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/scems56272.2022.9990639","pdf_url":null,"source":{"id":"https://openalex.org/S7407088006","display_name":"IEEE Student Conference on Electric Machines and Systems (SCEMS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2022 IEEE 5th Student Conference on Electric Machines and Systems (SCEMS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5059089579","display_name":"Jeong Han Lee","orcid":"https://orcid.org/0000-0002-1699-2660","observed_orcids":["https://orcid.org/0000-0002-1699-2660"]},"institutions":[{"id":"https://openalex.org/I80611190","display_name":"Jeonbuk National University","ror":"https://ror.org/05q92br09","country_code":"KR","type":"education","lineage":["https://openalex.org/I80611190"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeong Han Lee","raw_affiliation_strings":["Jeonbuk National University,Department of Electrical Engineering,Jeonju-si,Korea","Department of Electrical Engineering, Jeonbuk National University, Jeonju-si, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jeonbuk National University,Department of Electrical Engineering,Jeonju-si,Korea","institution_ids":["https://openalex.org/I80611190"]},{"raw_affiliation_string":"Department of Electrical Engineering, Jeonbuk National University, Jeonju-si, Korea","institution_ids":["https://openalex.org/I80611190"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110829244","display_name":"Jae Suk Lee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I80611190","display_name":"Jeonbuk National University","ror":"https://ror.org/05q92br09","country_code":"KR","type":"education","lineage":["https://openalex.org/I80611190"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae Suk Lee","raw_affiliation_strings":["Jeonbuk National University,Department of Electrical Engineering,Jeonju-si,Korea","Department of Electrical Engineering, Jeonbuk National University, Jeonju-si, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jeonbuk National University,Department of Electrical Engineering,Jeonju-si,Korea","institution_ids":["https://openalex.org/I80611190"]},{"raw_affiliation_string":"Department of Electrical Engineering, Jeonbuk National University, Jeonju-si, Korea","institution_ids":["https://openalex.org/I80611190"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I80611190"],"apc_list":null,"apc_paid":null,"fwci":0.1048,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.25010772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8784000277519226,"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":0.8784000277519226,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.057500001043081284,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0430000014603138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"trajectory optimization","score":0.9769999980926514},{"id":"https://openalex.org/keywords/route-optimization","display_name":"route optimization","score":0.9459999799728394},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9259999990463257},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"dynamic programming","score":0.9990000128746033},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":1.0},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7300000190734863},{"id":"https://openalex.org/keywords/computational-complexity","display_name":"computational complexity","score":0.7649999856948853},{"id":"https://openalex.org/keywords/algorithm-comparison","display_name":"algorithm comparison","score":0.6510000228881836}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8387339115142822},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.762451171875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.728008508682251},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5830721259117126},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5612204074859619},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.531643271446228},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5118931531906128},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.48321759700775146},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4611085057258606},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43089932203292847},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.42737966775894165},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.4200581908226013},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41478750109672546},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4027731120586395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32385876774787903},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24850603938102722},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.183041512966156},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08282792568206787},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/scems56272.2022.9990639","doi":"https://doi.org/10.1109/scems56272.2022.9990639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/scems56272.2022.9990639","pdf_url":null,"source":{"id":"https://openalex.org/S7407088006","display_name":"IEEE Student Conference on Electric Machines and Systems (SCEMS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2022 IEEE 5th Student Conference on Electric Machines and Systems (SCEMS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2050322675","https://openalex.org/W2112571391","https://openalex.org/W2117743062","https://openalex.org/W2149749146","https://openalex.org/W3033928040"],"related_works":["https://openalex.org/W2065869190","https://openalex.org/W2170141744","https://openalex.org/W2379986715","https://openalex.org/W3141565072","https://openalex.org/W6940783377","https://openalex.org/W4389475841","https://openalex.org/W2902806543","https://openalex.org/W2188018919","https://openalex.org/W1521228173","https://openalex.org/W4230996271"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"route":[3],"optimization":[4],"in":[5,92],"Markov":[6],"Decision":[7],"Process":[8],"(MDP)":[9],"environment":[10],"using":[11],"dynamic":[12],"programming":[13],"(DP)":[14],"and":[15,17,31,81,83,90],"Q-learning,":[16],"compares":[18],"features":[19],"of":[20,59,71,85],"two":[21],"algorithms.":[22],"Since":[23],"DP":[24,68,80],"uses":[25],"recursive":[26],"function,":[27],"coding":[28],"is":[29,65,77],"simple":[30],"easy":[32],"to":[33,41,45,67],"implement.":[34],"However,":[35],"all":[36],"cases":[37],"should":[38],"be":[39],"calculated":[40],"implement":[42],"DP.":[43,60],"Due":[44],"this":[46,62,93],"characteristic,":[47],"the":[48,54],"unnecessary":[49],"calculation":[50,72],"rate":[51],"increases":[52],"as":[53],"model":[55],"grows":[56],"for":[57,69],"implementation":[58],"In":[61],"paper,":[63],"learning":[64],"applied":[66],"reduction":[70],"complexity.":[73],"Same":[74],"MDP":[75],"problem":[76],"solved":[78],"by":[79],"Q-learning":[82],"results":[84],"each":[86],"case":[87],"are":[88],"compared":[89],"analyzed":[91],"paper.":[94]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-01-04T00:00:00"}