{"id":"https://openalex.org/W4415399111","doi":"https://doi.org/10.1109/spml66318.2025.11199827","title":"Multi-Agent Reinforcement Learning for Path Planning with Various Random and Fixed Obstacle Configurations","display_name":"Multi-Agent Reinforcement Learning for Path Planning with Various Random and Fixed Obstacle Configurations","publication_year":2025,"publication_date":"2025-07-15","ids":{"openalex":"https://openalex.org/W4415399111","doi":"https://doi.org/10.1109/spml66318.2025.11199827"},"language":null,"primary_location":{"id":"doi:10.1109/spml66318.2025.11199827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spml66318.2025.11199827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 8th International Conference on Signal Processing and Machine Learning (SPML)","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/A5010457984","display_name":"Jinglong Liu","orcid":"https://orcid.org/0000-0002-7934-1400"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinglong Liu","raw_affiliation_strings":["School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021099814","display_name":"Xitai Na","orcid":"https://orcid.org/0009-0001-2408-5753"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xitai Na","raw_affiliation_strings":["School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenda Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenda Wang","raw_affiliation_strings":["School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109156928","display_name":"Tuo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tuo Wang","raw_affiliation_strings":["School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenduo Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenduo Meng","raw_affiliation_strings":["School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017092775","display_name":"Jingdi Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdi Yan","raw_affiliation_strings":["School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25258419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9591000080108643,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11615","display_name":"Control and Dynamics of Mobile Robots","score":0.9508000016212463,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8672999739646912},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.6958000063896179},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.6800000071525574},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.5315999984741211},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.5217999815940857},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.46320000290870667}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8672999739646912},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6958000063896179},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.6800000071525574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6538000106811523},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5365999937057495},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.5217999815940857},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44999998807907104},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3971000015735626},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2603999972343445}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spml66318.2025.11199827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spml66318.2025.11199827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 8th International Conference on Signal Processing and Machine Learning (SPML)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2688642527","display_name":null,"funder_award_id":"62263025","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,69,93,107,110,125,131,143,158],"advancement":[2],"of":[3,12,53,118,166],"research":[4],"on":[5,27],"multi-agent":[6,21,44,153],"reinforcement":[7,18,30,61],"learning,":[8,65],"an":[9,37,76],"increasing":[10],"number":[11],"studies":[13],"have":[14],"begun":[15],"to":[16,20,83,116],"apply":[17],"learning":[19,31,62,101],"path":[22,33,45,154,172],"planning.":[23],"This":[24],"paper":[25,148],"focuses":[26],"using":[28],"distributed":[29],"for":[32,48,95,127],"planning":[34,46,155],"and":[35,40,55,63,73,102,121,129,157,171],"proposes":[36],"RAFO-A3C":[38,108],"(Random":[39],"fixed":[41,54],"obstacles":[42],"A3C)":[43],"algorithm":[47,59,79,144],"maps":[49],"with":[50,66,151],"mixed":[51],"forms":[52],"random":[56],"obstacles.":[57],"The":[58,78],"combines":[60],"imitation":[64],"A3C":[67],"as":[68,75],"main":[70],"training":[71],"method":[72],"odrM*":[74],"auxiliary.":[77],"learns":[80],"decentralized":[81],"strategies":[82,112],"plan":[84],"coordinated":[85],"paths":[86],"in":[87,138,146,164],"a":[88],"partially":[89],"observable":[90],"world":[91],"without":[92,124],"need":[94,126],"inter-agent":[96],"communication.":[97],"By":[98],"introducing":[99],"curriculum":[100],"multi-step":[103],"penalty":[104],"mechanisms":[105],"into":[106],"algorithm,":[109],"trained":[111],"can":[113],"be":[114],"applied":[115],"environments":[117],"different":[119],"sizes":[120],"obstacle":[122],"densities":[123],"retraining,":[128],"at":[130],"same":[132],"time,":[133,170],"avoid":[134],"agents":[135],"getting":[136],"stuck":[137],"oscillatory":[139],"ineffective":[140],"behaviors.":[141],"Finally,":[142],"proposed":[145],"this":[147],"is":[149],"compared":[150],"other":[152],"algorithms,":[156],"experimental":[159],"results":[160],"show":[161],"its":[162],"superiority":[163],"terms":[165],"success":[167],"rate,":[168],"completion":[169],"length.":[173]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-22T00:00:00"}