{"id":"https://openalex.org/W4362500609","doi":"https://doi.org/10.1109/access.2023.3264264","title":"A Controllable Agent by Subgoals in Path Planning Using Goal-Conditioned Reinforcement Learning","display_name":"A Controllable Agent by Subgoals in Path Planning Using Goal-Conditioned Reinforcement Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4362500609","doi":"https://doi.org/10.1109/access.2023.3264264"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3264264","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3264264","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10091554.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10091554.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045956362","display_name":"Gyeong Taek Lee","orcid":"https://orcid.org/0000-0003-4316-3072"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gyeong Taek Lee","raw_affiliation_strings":["Department of Industrial and Systems Engineering, Rutgers University, The State University of New Jersey, Piscataway, NJ, USA","A.I.mtory, 160, Yeoksam-ro, Gangnam-gu, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-4316-3072","affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, Rutgers University, The State University of New Jersey, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"A.I.mtory, 160, Yeoksam-ro, Gangnam-gu, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036574492","display_name":"Kangjin Kim","orcid":"https://orcid.org/0000-0002-3966-3309"},"institutions":[{"id":"https://openalex.org/I1283280774","display_name":"Brigham and Women's Hospital","ror":"https://ror.org/04b6nzv94","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283280774","https://openalex.org/I48633490"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kangjin Kim","raw_affiliation_strings":["Department of Medicine, Channing Division of Network Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3966-3309","affiliations":[{"raw_affiliation_string":"Department of Medicine, Channing Division of Network Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I1283280774","https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045956362"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.7065,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.70946987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"11","issue":null,"first_page":"33812","last_page":"33825"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7586754560470581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7157928943634033},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5737049579620361},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5215977430343628},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5207914710044861},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5043054819107056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3119741678237915},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2626870274543762},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13180303573608398},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09418797492980957}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7586754560470581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7157928943634033},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5737049579620361},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5215977430343628},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5207914710044861},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5043054819107056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3119741678237915},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2626870274543762},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13180303573608398},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09418797492980957},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3264264","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3264264","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10091554.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d73fe94e560e4585a6cf413555a72f31","is_oa":true,"landing_page_url":"https://doaj.org/article/d73fe94e560e4585a6cf413555a72f31","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 33812-33825 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3264264","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3264264","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10091554.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1884582016","display_name":null,"funder_award_id":"CCF-1445755","funder_id":"https://openalex.org/F4320310882","funder_display_name":"Center for Discrete Mathematics and Theoretical Computer Science"},{"id":"https://openalex.org/G7696778097","display_name":null,"funder_award_id":"1445755","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310882","display_name":"Center for Discrete Mathematics and Theoretical Computer Science","ror":"https://ror.org/00k551w06"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4362500609.pdf","grobid_xml":"https://content.openalex.org/works/W4362500609.grobid-xml"},"referenced_works_count":84,"referenced_works":["https://openalex.org/W2074684951","https://openalex.org/W2145339207","https://openalex.org/W2154852160","https://openalex.org/W2201581102","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2765371447","https://openalex.org/W2888116234","https://openalex.org/W2891816981","https://openalex.org/W2892051885","https://openalex.org/W2904121432","https://openalex.org/W2929352350","https://openalex.org/W2950170662","https://openalex.org/W2951001370","https://openalex.org/W2962702317","https://openalex.org/W2964067469","https://openalex.org/W2965930719","https://openalex.org/W2966477753","https://openalex.org/W2970414985","https://openalex.org/W2971481292","https://openalex.org/W2976344064","https://openalex.org/W2978873589","https://openalex.org/W2979229105","https://openalex.org/W2994067546","https://openalex.org/W2999840070","https://openalex.org/W3004297049","https://openalex.org/W3021675945","https://openalex.org/W3022583462","https://openalex.org/W3041521567","https://openalex.org/W3044457827","https://openalex.org/W3088197938","https://openalex.org/W3090434134","https://openalex.org/W3090573937","https://openalex.org/W3093571944","https://openalex.org/W3095315965","https://openalex.org/W3101007912","https://openalex.org/W3105107487","https://openalex.org/W3113470520","https://openalex.org/W3126082017","https://openalex.org/W3132669183","https://openalex.org/W3141426068","https://openalex.org/W3155121415","https://openalex.org/W3168659366","https://openalex.org/W3169053299","https://openalex.org/W3174288549","https://openalex.org/W3175752186","https://openalex.org/W3182036748","https://openalex.org/W3192902877","https://openalex.org/W3205322933","https://openalex.org/W3206041612","https://openalex.org/W3207330302","https://openalex.org/W4210366873","https://openalex.org/W4224244708","https://openalex.org/W4225427455","https://openalex.org/W4226265259","https://openalex.org/W4285601030","https://openalex.org/W4287126778","https://openalex.org/W4287994983","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6740801417","https://openalex.org/W6740879895","https://openalex.org/W6741002519","https://openalex.org/W6751540476","https://openalex.org/W6752089545","https://openalex.org/W6753060773","https://openalex.org/W6756303580","https://openalex.org/W6762640273","https://openalex.org/W6764173040","https://openalex.org/W6767047803","https://openalex.org/W6767649332","https://openalex.org/W6775584157","https://openalex.org/W6779463497","https://openalex.org/W6779780899","https://openalex.org/W6785279338","https://openalex.org/W6786644593","https://openalex.org/W6790601966","https://openalex.org/W6796180219","https://openalex.org/W6796226252","https://openalex.org/W6797805403","https://openalex.org/W6802965437","https://openalex.org/W6804551661","https://openalex.org/W6810733808","https://openalex.org/W6810906561"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W2359600231","https://openalex.org/W2380019117","https://openalex.org/W3138952546","https://openalex.org/W1987886368","https://openalex.org/W1660309994","https://openalex.org/W2369187583","https://openalex.org/W3197207153"],"abstract_inverted_index":{"The":[0],"aim":[1],"of":[2,93,105,118,149],"path":[3,10,74,148],"planning":[4],"is":[5],"to":[6,15,64,88,152,164],"search":[7],"for":[8,60,145],"a":[9,24,54,191],"from":[11,108,135],"the":[12,16,46,49,70,94,106,109,113,119,124,129,146,150,154,157,160,166,175,178,183,195,198],"starting":[13,137],"point":[14],"goal.":[17,27,155],"Numerous":[18],"studies,":[19],"however,":[20],"have":[21,41],"dealt":[22],"with":[23,201],"single":[25],"predefined":[26],"That":[28],"is,":[29],"an":[30,61],"agent":[31,62,107,120,130,151,161,176,184,196],"who":[32],"has":[33],"completed":[34],"learning":[35,57],"cannot":[36],"reach":[37,132,153,165],"other":[38],"goals":[39,168],"that":[40,128,169,182],"not":[42],"been":[43,172],"visited":[44,173],"in":[45,73],"training.":[47,179],"In":[48,139,156],"present":[50,142],"study,":[51],"we":[52,79,141],"propose":[53,84],"novel":[55],"reinforcement":[56],"(RL)":[58],"framework":[59],"reachable":[63],"any":[65,133,136],"subgoal":[66],"as":[67,69,190],"well":[68],"final":[71],"goal":[72],"planning.":[75],"To":[76],"do":[77],"this,":[78],"utilize":[80],"goal-conditioned":[81],"RL":[82],"and":[83,103,116,194],"bidirectional":[85,91],"memory":[86,97],"editing":[87,98],"obtain":[89],"various":[90,101,167],"trajectories":[92],"agent.":[95],"Bidirectional":[96],"can":[99,131],"generate":[100],"behavior":[102],"subgoals":[104,115,134],"limited":[110],"trajectory.":[111],"Then,":[112],"generated":[114],"behaviors":[117],"are":[121],"trained":[122],"on":[123],"policy":[125],"network":[126],"so":[127],"point.":[138],"addition,":[140],"reward":[143,202],"shaping":[144],"short":[147],"experimental":[158],"result,":[159],"was":[162],"able":[163],"had":[170],"never":[171],"by":[174],"during":[177],"We":[180],"confirmed":[181],"could":[185],"perform":[186],"difficult":[187],"missions,":[188],"such":[189],"round":[192],"trip,":[193],"used":[197],"shorter":[199],"route":[200],"shaping.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}