{"id":"https://openalex.org/W4386815480","doi":"https://doi.org/10.14428/esann/2023.es2023-46","title":"Automatic Trade-off Adaptation in Offline RL","display_name":"Automatic Trade-off Adaptation in Offline RL","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386815480","doi":"https://doi.org/10.14428/esann/2023.es2023-46"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2023.es2023-46","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2023.es2023-46","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-46","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.14428/esann/2023.es2023-46","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Phillip Swazinna","raw_affiliation_strings":[") Siemens Technology -Data Analytics & Artificial Intelligence Otto-Hahn-Ring 6, Munich, Germany",") TU Munich -School of Computation, Information, and Technology Boltzmannstrasse 3, Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":") Siemens Technology -Data Analytics & Artificial Intelligence Otto-Hahn-Ring 6, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":") TU Munich -School of Computation, Information, and Technology Boltzmannstrasse 3, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"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 Technology -Data Analytics & Artificial Intelligence Otto-Hahn-Ring 6, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":") Siemens Technology -Data Analytics & Artificial Intelligence Otto-Hahn-Ring 6, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002518694","display_name":"Thomas A. Runkler","orcid":"https://orcid.org/0000-0002-5465-198X"},"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"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Runkler","raw_affiliation_strings":[") Siemens Technology -Data Analytics & Artificial Intelligence Otto-Hahn-Ring 6, Munich, Germany",") TU Munich -School of Computation, Information, and Technology Boltzmannstrasse 3, Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":") Siemens Technology -Data Analytics & Artificial Intelligence Otto-Hahn-Ring 6, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":") TU Munich -School of Computation, Information, and Technology Boltzmannstrasse 3, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11552826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"309","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9887999892234802,"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/computer-science","display_name":"Computer science","score":0.8160229921340942},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6282681822776794},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.6211352348327637},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6031251549720764},{"id":"https://openalex.org/keywords/autopilot","display_name":"Autopilot","score":0.5159817337989807},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.43978801369667053},{"id":"https://openalex.org/keywords/adaptive-optimization","display_name":"Adaptive optimization","score":0.41458749771118164},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4024696350097656},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1732686460018158},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08970972895622253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8160229921340942},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6282681822776794},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.6211352348327637},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6031251549720764},{"id":"https://openalex.org/C18020424","wikidata":"https://www.wikidata.org/wiki/Q220858","display_name":"Autopilot","level":2,"score":0.5159817337989807},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.43978801369667053},{"id":"https://openalex.org/C149672232","wikidata":"https://www.wikidata.org/wiki/Q337048","display_name":"Adaptive optimization","level":2,"score":0.41458749771118164},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4024696350097656},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1732686460018158},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08970972895622253},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2023.es2023-46","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2023.es2023-46","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-46","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2023.es2023-46","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2023.es2023-46","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-46","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386815480.pdf","grobid_xml":"https://content.openalex.org/works/W4386815480.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2127130980","https://openalex.org/W2491035845","https://openalex.org/W2760661167","https://openalex.org/W3048481719","https://openalex.org/W3178225342","https://openalex.org/W4225110331","https://openalex.org/W4281490069","https://openalex.org/W4284713200","https://openalex.org/W4311248723","https://openalex.org/W6838915746"],"related_works":["https://openalex.org/W2528333064","https://openalex.org/W2357122534","https://openalex.org/W2148668825","https://openalex.org/W2159456118","https://openalex.org/W4287557383","https://openalex.org/W2268481623","https://openalex.org/W2169677720","https://openalex.org/W2350405024","https://openalex.org/W3112224989","https://openalex.org/W2539723359"],"abstract_inverted_index":{"Recently,":[0],"offline":[1],"RL":[2],"algorithms":[3],"have":[4],"been":[5],"proposed":[6],"that":[7,76],"remain":[8],"adaptive":[9],"at":[10,37],"runtime.":[11,38],"For":[12],"example,":[13],"the":[14,19,26,34,47,71,79,83],"LION":[15],"algorithm":[16,88],"[1]":[17],"provides":[18],"user":[20],"with":[21,73],"an":[22,74],"interface":[23,44],"to":[24,45,51],"set":[25],"trade-off":[27,58],"between":[28,59],"behavior":[29,49],"cloning":[30],"and":[31,54,61],"optimality":[32],"w.r.t.":[33],"estimated":[35],"return":[36],"Experts":[39],"can":[40],"then":[41],"use":[42],"this":[43],"adapt":[46],"policy":[48],"according":[50],"their":[52],"preferences":[53],"find":[55],"a":[56,86],"good":[57],"conservatism":[60],"performance":[62],"optimization.":[63],"Since":[64],"expert":[65],"time":[66],"is":[67],"precious,":[68],"we":[69,90],"extend":[70],"methodology":[72],"autopilot":[75],"automatically":[77],"finds":[78],"best":[80],"parameterization":[81],"of":[82],"trade-off,":[84],"yielding":[85],"new":[87],"which":[89],"term":[91],"AutoLION.":[92]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
