{"id":"https://openalex.org/W4320057363","doi":"https://doi.org/10.1145/3573834.3574534","title":"Urban Path Planning Based on Improved Model-based Reinforcement Learning Algorithm","display_name":"Urban Path Planning Based on Improved Model-based Reinforcement Learning Algorithm","publication_year":2022,"publication_date":"2022-11-25","ids":{"openalex":"https://openalex.org/W4320057363","doi":"https://doi.org/10.1145/3573834.3574534"},"language":"en","primary_location":{"id":"doi:10.1145/3573834.3574534","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3573834.3574534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Advanced Information Science and System","raw_type":"proceedings-article"},"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/A5073187657","display_name":"Huimin Wang","orcid":"https://orcid.org/0000-0003-1507-5040"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin Wang","raw_affiliation_strings":["Anhui University, China"],"raw_orcid":"https://orcid.org/0000-0003-1507-5040","affiliations":[{"raw_affiliation_string":"Anhui University, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060459519","display_name":"Dong Liang","orcid":"https://orcid.org/0000-0002-3052-6068"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Liang","raw_affiliation_strings":["Anhui University, China"],"raw_orcid":"https://orcid.org/0000-0002-3052-6068","affiliations":[{"raw_affiliation_string":"Anhui University, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085350749","display_name":"Yuliang Xi","orcid":"https://orcid.org/0000-0003-1933-0934"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuliang Xi","raw_affiliation_strings":["Anhui University, China"],"raw_orcid":"https://orcid.org/0000-0003-1933-0934","affiliations":[{"raw_affiliation_string":"Anhui University, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.996399998664856,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9883000254631042,"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":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.799967348575592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6859993934631348},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5787892937660217},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5483921766281128},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41249966621398926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4088881313800812},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3262154459953308},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1297387182712555},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.09282398223876953}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.799967348575592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6859993934631348},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5787892937660217},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5483921766281128},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41249966621398926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4088881313800812},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3262154459953308},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1297387182712555},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.09282398223876953},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573834.3574534","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3573834.3574534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Advanced Information Science and System","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1598952354","https://openalex.org/W1969483458","https://openalex.org/W2082569289","https://openalex.org/W2149565728","https://openalex.org/W2165726932","https://openalex.org/W2765161525","https://openalex.org/W3126616698","https://openalex.org/W3167509898","https://openalex.org/W3211443552","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W4306904969","https://openalex.org/W4289260319","https://openalex.org/W2359600231","https://openalex.org/W2380019117","https://openalex.org/W3138952546","https://openalex.org/W1660309994","https://openalex.org/W2369187583","https://openalex.org/W3197207153"],"abstract_inverted_index":{"With":[0],"the":[1,4,8,18,60,64,80,99,102,107,113,116,126,132,137,140,149,154,159,171,177,181,191,194,207,221],"development":[2],"of":[3,11,63,109,115,180,193,196,209,226],"urban":[5,24],"economy,":[6],"and":[7,32,96,136,158,199,213],"continuous":[9],"expansion":[10],"vehicle":[12],"scale,":[13],"traf\ufb01c":[14,92],"congestion":[15,69],"has":[16,41],"become":[17,42],"most":[19],"serious":[20],"problem":[21],"affecting":[22],"contemporary":[23],"development.":[25],"Using":[26],"advanced":[27],"road":[28,39,86,90,146,185],"network":[29,87,91,147,186],"information":[30],"perception":[31],"transmission":[33],"technologies,":[34],"path":[35,65],"planning":[36,57,66],"under":[37,183],"real-time":[38],"conditions":[40],"an":[43],"important":[44],"means":[45],"to":[46,71,120,139,216],"solve":[47,121],"this":[48,122,169],"problem.":[49],"Previously,":[50],"our":[51],"proposed":[52],"model-based":[53,173],"reinforcement":[54,210,227],"learning":[55,211,228],"multipath":[56],"algorithm":[58,117,182],"realized":[59],"rapid":[61],"response":[62],"result,":[67],"alleviating":[68],"drift":[70],"a":[72],"certain":[73,163],"extent.":[74],"However,":[75],"further":[76],"research":[77],"shows":[78],"that":[79,106,152],"model":[81,110,141],"performs":[82],"poorly":[83],"in":[84,128,168,220],"extreme":[85,184],"environments":[88],"(the":[89],"pressure":[93],"is":[94,105,166],"0)":[95],"cannot":[97],"explore":[98,125,224],"complete":[100],"path,":[101],"main":[103],"reason":[104],"effect":[108],"hyperparameters":[111,127,197,225],"on":[112,206],"convergence":[114,142,178,208],"was":[118],"ignored.":[119],"problems,":[123],"we":[124,214],"detail,":[129],"especially":[130],"discuss":[131],"discount":[133,155],"factor":[134,156],"\u03b3":[135,157,198],"finalReward":[138,160,200],"by":[143],"using":[144],"Shenzhen":[145],"data.":[148],"results":[150],"show":[151],"when":[153],"value":[161],"satisfy":[162],"conditions,":[164],"which":[165,223],"obtained":[167],"study,":[170],"improved":[172],"method":[174],"can":[175],"guarantee":[176],"stability":[179],"environments.":[187],"This":[188],"paper":[189],"reveals":[190],"importance":[192],"design":[195],"as":[201,203],"well":[202],"their":[204],"interrelationship":[205],"algorithms":[212],"hope":[215],"give":[217],"some":[218],"insights":[219],"field":[222],"algorithm.":[229]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}