{"id":"https://openalex.org/W4408062225","doi":"https://doi.org/10.5220/0013143800003890","title":"Curiosity Driven Reinforcement Learning for Job Shop Scheduling","display_name":"Curiosity Driven Reinforcement Learning for Job Shop Scheduling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408062225","doi":"https://doi.org/10.5220/0013143800003890"},"language":"en","primary_location":{"id":"doi:10.5220/0013143800003890","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013143800003890","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0013143800003890","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093936443","display_name":"Alexander Nasuta","orcid":"https://orcid.org/0009-0007-5111-6774"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Nasuta","raw_affiliation_strings":["Chair of Intelligence in Quality Sensing, RWTH Aachen, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Intelligence in Quality Sensing, RWTH Aachen, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019787331","display_name":"Marco Kemmerling","orcid":"https://orcid.org/0000-0003-0141-2050"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco Kemmerling","raw_affiliation_strings":["Chair of Intelligence in Quality Sensing, RWTH Aachen, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Intelligence in Quality Sensing, RWTH Aachen, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048041966","display_name":"Hans Aoyang Zhou","orcid":"https://orcid.org/0000-0002-7768-4303"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hans Zhou","raw_affiliation_strings":["Chair of Intelligence in Quality Sensing, RWTH Aachen, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Intelligence in Quality Sensing, RWTH Aachen, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017362418","display_name":"Anas Abdelrazeq","orcid":"https://orcid.org/0000-0002-8450-2889"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anas Abdelrazeq","raw_affiliation_strings":["Chair of Intelligence in Quality Sensing, RWTH Aachen, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Intelligence in Quality Sensing, RWTH Aachen, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045094368","display_name":"Robert Schmitt","orcid":"https://orcid.org/0000-0002-0011-5962"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robert H. Schmitt","raw_affiliation_strings":["Chair of Intelligence in Quality Sensing, RWTH Aachen, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Intelligence in Quality Sensing, RWTH Aachen, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03634267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.9435999989509583,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.9435999989509583,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.779030442237854},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6364045143127441},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6165772080421448},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5213900208473206},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4466342628002167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.331382155418396},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2840689420700073},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.17872074246406555},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.14366397261619568},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1370021104812622}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.779030442237854},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6364045143127441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6165772080421448},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5213900208473206},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4466342628002167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.331382155418396},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2840689420700073},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.17872074246406555},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.14366397261619568},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1370021104812622}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0013143800003890","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013143800003890","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.rwth-aachen.de:1006836","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/1006836","pdf_url":"https://publications.rwth-aachen.de/record/1006836/files/1006836.pdf","source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 17th International Conference on Agents and Artificial Intelligence - (Volume 2) February 23-25, 2025, in Porto, Portugal / Editors: Ana Paula Rocha, Luc Steels and H. Jaap van den Herik<br/>17. International Conference on Agents and Artificial Intelligence, ICAART 2025, Porto, Portugal, 2025-02-23 - 2025-02-25","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.5220/0013143800003890","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013143800003890","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.6299999952316284,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G3693894647","display_name":"Flexibilization of complex Ecosystems using Democratic AI based Decision Support and Recommendation Systems at Work","funder_award_id":"101069499","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W4382584175","https://openalex.org/W2123270665","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W4252460700","https://openalex.org/W4401386752"],"abstract_inverted_index":{"The":[0],"Job":[1],"Shop":[2],"Problem":[3],"(JSP)":[4],"is":[5,19,148],"a":[6,35,60],"well-known":[7],"NP-hard":[8],"problem":[9],"with":[10,93,149],"numerous":[11],"applications":[12],"in":[13,25,29,75,91],"manufacturing":[14,27],"and":[15,108,138,158],"other":[16],"fields.Efficient":[17],"scheduling":[18],"critical":[20],"for":[21,69],"producing":[22],"customized":[23],"products":[24],"the":[26,31,39,100,103,121,127,133,136,146],"industry":[28],"time.Typically,":[30],"quality":[32],"metrics":[33],"of":[34,102,123,129,143],"schedule,":[36],"such":[37],"as":[38,59],"makespan,":[40],"can":[41],"only":[42],"be":[43],"assessed":[44],"after":[45],"all":[46],"tasks":[47],"have":[48,85],"been":[49,86],"assigned,":[50],"leading":[51],"to":[52,88,154],"sparse":[53,94],"reward":[54,83,140],"signals":[55,141],"when":[56],"framing":[57],"JSP":[58],"reinforcement":[61],"learning":[62,77,90],"(RL)":[63],"problem.Sparse":[64],"rewards":[65],"pose":[66],"significant":[67],"challenges":[68],"many":[70],"RL":[71,134],"algorithms,":[72,79],"often":[73],"resulting":[74],"slow":[76],"behavior.Curiosity":[78],"which":[80],"introduce":[81],"intrinsic":[82,137],"signals,":[84],"shown":[87],"accelerate":[89],"environments":[92],"rewards.In":[95],"this":[96],"study,":[97],"we":[98],"explored":[99],"effectiveness":[101],"Intrinsic":[104],"Curiosity":[105,110],"Module":[106],"(ICM)":[107],"Episodic":[109],"(EC)":[111],"by":[112,132],"benchmarking":[113],"them":[114],"against":[115],"state-of-the-art":[116],"methods.Our":[117],"experiments":[118],"demonstrate":[119],"that":[120],"use":[122],"curiosity":[124],"significantly":[125],"increases":[126],"amount":[128],"states":[130],"encountered":[131],"agent.When":[135],"extrinsic":[139],"are":[142,152],"comparable":[144],"magnitude,":[145],"agent":[147],"ICM":[150],"module":[151],"able":[153],"escape":[155],"local":[156],"optima":[157],"discover":[159],"better":[160],"solutions.":[161]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}
