{"id":"https://openalex.org/W3112977404","doi":"https://doi.org/10.5220/0010189500280037","title":"SAT-MARL: Specification Aware Training in Multi-Agent Reinforcement Learning","display_name":"SAT-MARL: Specification Aware Training in Multi-Agent Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3112977404","doi":"https://doi.org/10.5220/0010189500280037","mag":"3112977404"},"language":"en","primary_location":{"id":"doi:10.5220/0010189500280037","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010189500280037","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 13th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0010189500280037","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020217059","display_name":"Fabian Ritz","orcid":"https://orcid.org/0000-0001-7707-1358"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Fabian Ritz","raw_affiliation_strings":["Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024645861","display_name":"Thomy Phan","orcid":"https://orcid.org/0000-0002-4390-8954"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomy Phan","raw_affiliation_strings":["Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052914309","display_name":"Robert M\u00fcller","orcid":"https://orcid.org/0000-0003-3108-713X"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robert M\u00fcller","raw_affiliation_strings":["Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062401089","display_name":"Thomas Gabor","orcid":"https://orcid.org/0000-0003-2048-8667"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Gabor","raw_affiliation_strings":["Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024006892","display_name":"Andreas Sedlmeier","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Sedlmeier","raw_affiliation_strings":["Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010282514","display_name":"Marc Zeller","orcid":"https://orcid.org/0000-0002-6738-7903"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marc Zeller","raw_affiliation_strings":["Corporate Technology (CT), Siemens AG, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Corporate Technology (CT), Siemens AG, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038406626","display_name":"Jan Wieghardt","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Wieghardt","raw_affiliation_strings":["Corporate Technology (CT), Siemens AG, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Corporate Technology (CT), Siemens AG, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000700365","display_name":"Reiner Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reiner Schmid","raw_affiliation_strings":["Corporate Technology (CT), Siemens AG, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Corporate Technology (CT), Siemens AG, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042812936","display_name":"Horst Sauer","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Horst Sauer","raw_affiliation_strings":["Corporate Technology (CT), Siemens AG, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Corporate Technology (CT), Siemens AG, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041172705","display_name":"Cornel Klein","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornel Klein","raw_affiliation_strings":["Corporate Technology (CT), Siemens AG, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Corporate Technology (CT), Siemens AG, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064469861","display_name":"Claudia Linnhoff\u2010Popien","orcid":"https://orcid.org/0000-0001-6284-9286"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudia Linnhoff-Popien","raw_affiliation_strings":["Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5020217059"],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":0.5644143,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70959056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"28","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9933000206947327,"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":0.9933000206947327,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9794999957084656,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10260","display_name":"Software Engineering Research","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8645399212837219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7050977945327759},{"id":"https://openalex.org/keywords/factory","display_name":"Factory (object-oriented programming)","score":0.6660289764404297},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.588677167892456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4708912968635559},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.45893073081970215},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.4246179461479187},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.42128533124923706},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32656940817832947},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18096065521240234}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8645399212837219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7050977945327759},{"id":"https://openalex.org/C40149104","wikidata":"https://www.wikidata.org/wiki/Q5620977","display_name":"Factory (object-oriented programming)","level":2,"score":0.6660289764404297},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.588677167892456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4708912968635559},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.45893073081970215},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.4246179461479187},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.42128533124923706},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32656940817832947},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18096065521240234},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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:10.5220/0010189500280037","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010189500280037","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 13th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2012.07949","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.07949","pdf_url":"https://arxiv.org/pdf/2012.07949","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.5220/0010189500280037","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010189500280037","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 13th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1579184372","https://openalex.org/W1777239053","https://openalex.org/W1845972764","https://openalex.org/W2033406822","https://openalex.org/W2121863487","https://openalex.org/W2122763142","https://openalex.org/W2145339207","https://openalex.org/W2151382427","https://openalex.org/W2161061197","https://openalex.org/W2189058185","https://openalex.org/W2296073425","https://openalex.org/W2296452361","https://openalex.org/W2405769265","https://openalex.org/W2462906003","https://openalex.org/W2507578125","https://openalex.org/W2594794854","https://openalex.org/W2617547828","https://openalex.org/W2620974420","https://openalex.org/W2626275188","https://openalex.org/W2766447205","https://openalex.org/W2768629321","https://openalex.org/W2768908787","https://openalex.org/W2794643322","https://openalex.org/W2807741983","https://openalex.org/W2810602713","https://openalex.org/W2891217993","https://openalex.org/W2911616846","https://openalex.org/W2946606218","https://openalex.org/W2949963774","https://openalex.org/W2962896606","https://openalex.org/W2962938168","https://openalex.org/W2963658727","https://openalex.org/W2963771109","https://openalex.org/W2964345382","https://openalex.org/W2978639576","https://openalex.org/W3093287223","https://openalex.org/W3117280628","https://openalex.org/W4295598622"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"A":[0],"characteristic":[1],"of":[2],"reinforcement":[3,99],"learning":[4,100],"is":[5],"the":[6,50,79,115],"ability":[7],"to":[8,40,52,55,64,93],"develop":[9],"unforeseen":[10],"strategies":[11,17],"when":[12],"solving":[13],"problems.":[14],"While":[15],"such":[16],"sometimes":[18],"yield":[19],"superior":[20],"performance,":[21],"they":[22],"may":[23],"also":[24,38],"result":[25],"in":[26],"undesired":[27],"or":[28],"even":[29],"dangerous":[30],"behavior.":[31],"In":[32],"industrial":[33,87],"scenarios,":[34],"a":[35,58,82],"system's":[36],"behavior":[37],"needs":[39],"be":[41,112],"predictable":[42],"and":[43,68,96,108],"lie":[44],"within":[45],"defined":[46],"ranges.":[47],"To":[48],"enable":[49],"agents":[51,95],"learn":[53],"(how)":[54],"align":[56],"with":[57,91,106],"given":[59],"specification,":[60],"this":[61],"paper":[62],"proposes":[63],"explicitly":[65],"transfer":[66],"functional":[67,107],"non-functional":[69,109],"requirements":[70],"into":[71],"shaped":[72],"rewards.":[73],"Experiments":[74],"are":[75],"carried":[76],"out":[77],"on":[78],"smart":[80],"factory,":[81],"multi-agent":[83,98],"environment":[84],"modeling":[85],"an":[86],"lot-size-one":[88],"production":[89],"facility,":[90],"up":[92],"eight":[94],"different":[97],"algorithms.":[101],"Results":[102],"indicate":[103],"that":[104],"compliance":[105],"constraints":[110],"can":[111],"achieved":[113],"by":[114],"proposed":[116],"approach.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}