{"id":"https://openalex.org/W4390481878","doi":"https://doi.org/10.1109/ssci52147.2023.10371978","title":"Learning Control Policies for Variable Objectives from Offline Data","display_name":"Learning Control Policies for Variable Objectives from Offline Data","publication_year":2023,"publication_date":"2023-12-05","ids":{"openalex":"https://openalex.org/W4390481878","doi":"https://doi.org/10.1109/ssci52147.2023.10371978"},"language":"en","primary_location":{"id":"doi:10.1109/ssci52147.2023.10371978","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ssci52147.2023.10371978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5101770641","display_name":"M. Weber","orcid":"https://orcid.org/0000-0002-3639-2267"},"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 Weber","raw_affiliation_strings":["Siemens AG, Technology,Munich,Germany","Siemens AG, Technology, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG, Technology,Munich,Germany","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"Siemens AG, Technology, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005487112","display_name":"Phillip Swazinna","orcid":"https://orcid.org/0000-0003-4667-9584"},"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":"Phillip Swazinna","raw_affiliation_strings":["Siemens AG, Technology,Munich,Germany","Siemens AG, Technology, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG, Technology,Munich,Germany","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"Siemens AG, Technology, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003471349","display_name":"Daniel Hein","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":"Daniel Hein","raw_affiliation_strings":["Siemens AG, Technology,Munich,Germany","Siemens AG, Technology, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG, Technology,Munich,Germany","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"Siemens AG, Technology, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035246650","display_name":"Steffen Udluft","orcid":"https://orcid.org/0000-0002-5767-2591"},"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":"Steffen Udluft","raw_affiliation_strings":["Siemens AG, Technology,Munich,Germany","Siemens AG, Technology, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG, Technology,Munich,Germany","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"Siemens AG, Technology, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018582427","display_name":"Volkmar Sterzing","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":"Volkmar Sterzing","raw_affiliation_strings":["Siemens AG, Technology,Munich,Germany","Siemens AG, Technology, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG, Technology,Munich,Germany","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"Siemens AG, Technology, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1325886976"],"apc_list":null,"apc_paid":null,"fwci":0.3226,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6720096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1674","last_page":"1681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996999979019165,"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":0.996999979019165,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9731000065803528,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9718000292778015,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7808139324188232},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733990490436554},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6520084142684937},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.6246585249900818},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5512672662734985},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4657467305660248},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4300912618637085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3897715210914612},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3727426528930664},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08773845434188843}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7808139324188232},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733990490436554},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6520084142684937},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.6246585249900818},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5512672662734985},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4657467305660248},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4300912618637085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3897715210914612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3727426528930664},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08773845434188843},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci52147.2023.10371978","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ssci52147.2023.10371978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W58266590","https://openalex.org/W166862392","https://openalex.org/W1552327263","https://openalex.org/W1966630946","https://openalex.org/W2001371858","https://openalex.org/W2120346334","https://openalex.org/W2143770247","https://openalex.org/W2169673701","https://openalex.org/W2618033804","https://openalex.org/W2625286567","https://openalex.org/W2760661167","https://openalex.org/W2947150733","https://openalex.org/W2991355586","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3099427826","https://openalex.org/W3103474936","https://openalex.org/W3170197122","https://openalex.org/W3178225342","https://openalex.org/W4212774754","https://openalex.org/W4225110331","https://openalex.org/W4285601030","https://openalex.org/W4293872189","https://openalex.org/W4297792190","https://openalex.org/W4298857966","https://openalex.org/W6616173779","https://openalex.org/W6677737365","https://openalex.org/W6680657880","https://openalex.org/W6713841817","https://openalex.org/W6733985435","https://openalex.org/W6748012927","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6785423136","https://openalex.org/W6790767801","https://openalex.org/W6791413555","https://openalex.org/W6810277566","https://openalex.org/W6838254935","https://openalex.org/W6847640412"],"related_works":["https://openalex.org/W2075768550","https://openalex.org/W3022218857","https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W2369178846","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W2370289839","https://openalex.org/W3125814499"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"provides":[3],"a":[4,31,54],"viable":[5],"approach":[6],"to":[7,50,73,80],"obtain":[8],"advanced":[9],"control":[10],"strategies":[11],"for":[12,34,92],"dynamical":[13],"systems,":[14],"in":[15],"particular":[16],"when":[17],"direct":[18],"interaction":[19],"with":[20],"the":[21,60,68,74,78],"environment":[22],"is":[23],"not":[24],"available.":[25],"In":[26],"this":[27,45],"paper,":[28],"we":[29],"introduce":[30],"conceptual":[32],"extension":[33],"model-based":[35],"policy":[36,42],"search":[37],"methods,":[38],"called":[39],"variable":[40],"objective":[41],"(VOP).":[43],"With":[44],"approach,":[46],"policies":[47],"are":[48],"trained":[49],"generalize":[51],"efficiently":[52],"over":[53],"variety":[55],"of":[56],"objectives,":[57],"which":[58],"parameterize":[59],"reward":[61],"function.":[62],"We":[63],"demonstrate":[64],"that":[65],"by":[66],"altering":[67],"objectives":[69],"passed":[70],"as":[71],"input":[72],"policy,":[75],"users":[76],"gain":[77],"freedom":[79],"adjust":[81],"its":[82],"behavior":[83],"or":[84,97],"re-balance":[85],"optimization":[86],"targets":[87],"at":[88],"runtime,":[89],"without":[90],"need":[91],"collecting":[93],"additional":[94],"observation":[95],"batches":[96],"re-training.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}