{"id":"https://openalex.org/W7130534967","doi":"https://doi.org/10.1109/ictc66702.2025.11388039","title":"Generative AI-based Offline Reinforcement Learning for Trajectory Planning","display_name":"Generative AI-based Offline Reinforcement Learning for Trajectory Planning","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130534967","doi":"https://doi.org/10.1109/ictc66702.2025.11388039"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11388039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","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/A5114243483","display_name":"Chaemoon Im","orcid":"https://orcid.org/0009-0009-7270-7332"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chaemoon Im","raw_affiliation_strings":["Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642851","display_name":"Byung\u2010Soo Kim","orcid":"https://orcid.org/0000-0001-5210-7430"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bohyeon Kim","raw_affiliation_strings":["Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041027404","display_name":"Junsu Kim","orcid":"https://orcid.org/0000-0001-9583-7978"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joongheon Kim","raw_affiliation_strings":["Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"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":null,"issue":null,"first_page":"825","last_page":"827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8256999850273132,"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":0.8256999850273132,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.03280000016093254,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.01979999989271164,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8543000221252441},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5480999946594238},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.47269999980926514},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4645000100135803},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3732999861240387},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.34610000252723694}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8543000221252441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7027000188827515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6976000070571899},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5670999884605408},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5480999946594238},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.47269999980926514},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4645000100135803},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3732999861240387},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.34139999747276306},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26339998841285706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11388039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337495","display_name":"Technology Development","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W3163699750","https://openalex.org/W4214717370","https://openalex.org/W4308438248","https://openalex.org/W4360584316","https://openalex.org/W4385403811","https://openalex.org/W4392477589","https://openalex.org/W4402305492","https://openalex.org/W4402402057","https://openalex.org/W4412071376","https://openalex.org/W4412445535"],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"reinforcement":[1,57],"learning":[2,58],"(RL)":[3],"algorithms":[4],"faces":[5],"several":[6],"problems":[7],"such":[8],"as":[9],"danger":[10,43],"and":[11],"cost":[12],"for":[13,22],"collecting":[14],"data":[15],"from":[16,35,44,69],"the":[17,36,42,48,70,75,78,84],"environment,":[18],"degrading":[19],"its":[20],"potential":[21,76],"real-world":[23],"application.":[24],"As":[25],"an":[26],"alternative,":[27],"offline":[28,56],"RL,":[29,80],"which":[30,60],"aims":[31],"to":[32,40,64],"learn":[33],"policy":[34,68],"dataset,":[37],"is":[38],"proposed":[39],"remove":[41],"real-time":[45],"interaction":[46],"with":[47],"environment.":[49],"Among":[50],"them,":[51],"this":[52],"paper":[53],"proposes":[54],"diffusion-based":[55,79],"algorithm":[59],"adopts":[61],"diffusion":[62],"model":[63],"better":[65],"extract":[66],"useful":[67],"dataset.":[71],"Experiment":[72],"results":[73],"shows":[74],"of":[77,83],"in":[81],"terms":[82],"maximized":[85],"reward.":[86]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}