{"id":"https://openalex.org/W4415744042","doi":"https://doi.org/10.1109/qrs-c65679.2025.00104","title":"Graph-Contextual Reinforcement Learning for Efficient Exploration in Directed Controller Synthesis","display_name":"Graph-Contextual Reinforcement Learning for Efficient Exploration in Directed Controller Synthesis","publication_year":2025,"publication_date":"2025-07-16","ids":{"openalex":"https://openalex.org/W4415744042","doi":"https://doi.org/10.1109/qrs-c65679.2025.00104"},"language":null,"primary_location":{"id":"doi:10.1109/qrs-c65679.2025.00104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qrs-c65679.2025.00104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 25th International Conference on Software Quality, Reliability, and Security Companion (QRS-C)","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/A5117649531","display_name":"Toshihide Ubukata","orcid":"https://orcid.org/0009-0004-1033-3383"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Toshihide Ubukata","raw_affiliation_strings":["Waseda University,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405281","display_name":"Mingyue Zhang","orcid":"https://orcid.org/0000-0002-3003-8902"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyue Zhang","raw_affiliation_strings":["Southwest University,China"],"affiliations":[{"raw_affiliation_string":"Southwest University,China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047307000","display_name":"Takuto Yamauchi","orcid":"https://orcid.org/0009-0006-0398-4588"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuto Yamauchi","raw_affiliation_strings":["Waseda University,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100708120","display_name":"Jialong Li","orcid":"https://orcid.org/0009-0002-9742-3044"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jialong Li","raw_affiliation_strings":["Waseda University,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045332896","display_name":"Kenji Tei","orcid":"https://orcid.org/0000-0003-1106-1709"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenji Tei","raw_affiliation_strings":["Institute of Science Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo,Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5117649531"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16551401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"777","last_page":"779"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.25369998812675476,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.25369998812675476,"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/T10142","display_name":"Formal Methods in Verification","score":0.13019999861717224,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09109999984502792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7070000171661377},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5590000152587891},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4991999864578247},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48010000586509705},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.44620001316070557},{"id":"https://openalex.org/keywords/directed-graph","display_name":"Directed graph","score":0.4424000084400177},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.44029998779296875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.708299994468689},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7070000171661377},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5590000152587891},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4991999864578247},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.44620001316070557},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41510000824928284},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26089999079704285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/qrs-c65679.2025.00104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qrs-c65679.2025.00104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 25th International Conference on Software Quality, Reliability, and Security Companion (QRS-C)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2895957339","https://openalex.org/W3112265777","https://openalex.org/W4309495345","https://openalex.org/W4382866769"],"related_works":[],"abstract_inverted_index":{"Controller":[0],"synthesis":[1,24],"is":[2],"a":[3,61],"formal":[4],"method":[5],"for":[6],"automatically":[7],"generating":[8],"LTS":[9,57],"(Labeled":[10],"Transition":[11],"System)":[12],"controllers":[13],"that":[14],"satisfy":[15],"given":[16],"properties.":[17],"However,":[18],"the":[19,56,71,84],"efficiency":[20],"of":[21,83],"directed":[22],"controller":[23],"critically":[25],"depends":[26],"on":[27,36,70],"exploration":[28,58,86],"policies,":[29],"which":[30,44],"are":[31],"often":[32],"hand-crafted":[33],"or":[34],"based":[35],"limited":[37],"current":[38],"features.":[39],"This":[40],"paper":[41],"proposes":[42],"GCRL,":[43],"integrates":[45],"Graph":[46],"Neural":[47],"Networks":[48],"(GNNs)":[49],"with":[50],"Reinforcement":[51],"Learning":[52],"(RL)":[53],"to":[54],"encode":[55],"history":[59],"as":[60],"graph":[62],"structure,":[63],"thereby":[64],"capturing":[65],"additional":[66],"non-current-based":[67],"context.":[68],"Experiments":[69],"Transfer":[72],"Line":[73],"benchmark":[74],"demonstrate":[75],"faster":[76],"convergence":[77],"during":[78],"training":[79],"and":[80],"improved":[81],"generalization":[82],"learned":[85],"policies.":[87]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-31T00:00:00"}