{"id":"https://openalex.org/W4404448323","doi":"https://doi.org/10.1007/978-3-031-75778-5_2","title":"Safe Reinforcement Learning Through Regret and\u00a0State Restorations in\u00a0Evaluation Stages","display_name":"Safe Reinforcement Learning Through Regret and\u00a0State Restorations in\u00a0Evaluation Stages","publication_year":2024,"publication_date":"2024-11-17","ids":{"openalex":"https://openalex.org/W4404448323","doi":"https://doi.org/10.1007/978-3-031-75778-5_2"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-75778-5_2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-75778-5_2","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","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/A5033310691","display_name":"Timo P. Gros","orcid":"https://orcid.org/0000-0002-1100-1952"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Timo P. Gros","raw_affiliation_strings":["Center for European Research in Trusted Artificial Intelligence (CERTAIN), Saarbr\u00fccken, Germany","German Research Center for Artificial Intelligence (DFKI), Saarbr\u00fccken, Germany","Saarland University, Saarland Informatics Campus, Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1100-1952","affiliations":[{"raw_affiliation_string":"Center for European Research in Trusted Artificial Intelligence (CERTAIN), Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI), Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Saarland University, Saarland Informatics Campus, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090443322","display_name":"N. M\u00fcller","orcid":"https://orcid.org/0000-0002-5932-3395"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nicola J. M\u00fcller","raw_affiliation_strings":["Center for European Research in Trusted Artificial Intelligence (CERTAIN), Saarbr\u00fccken, Germany","Saarland University, Saarland Informatics Campus, Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5932-3395","affiliations":[{"raw_affiliation_string":"Center for European Research in Trusted Artificial Intelligence (CERTAIN), Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Saarland University, Saarland Informatics Campus, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065705708","display_name":"Daniel H\u00f6ller","orcid":"https://orcid.org/0000-0002-2776-9288"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel H\u00f6ller","raw_affiliation_strings":["Saarland University, Saarland Informatics Campus, Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2776-9288","affiliations":[{"raw_affiliation_string":"Saarland University, Saarland Informatics Campus, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089228948","display_name":"Verena Wolf","orcid":"https://orcid.org/0000-0001-8460-6007"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Verena Wolf","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI), Saarbr\u00fccken, Germany","Saarland University, Saarland Informatics Campus, Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8460-6007","affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI), Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Saarland University, Saarland Informatics Campus, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033310691"],"corresponding_institution_ids":["https://openalex.org/I33256026","https://openalex.org/I91712215"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58140527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962999820709229,"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":0.9962999820709229,"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/T10260","display_name":"Software Engineering Research","score":0.9616000056266785,"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/regret","display_name":"Regret","score":0.9320564270019531},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7901068925857544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7816444635391235},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.470651775598526},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4227645695209503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4040074348449707},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33796870708465576},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2275679111480713},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1048879325389862},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07190948724746704},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06102606654167175}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9320564270019531},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7901068925857544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7816444635391235},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.470651775598526},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4227645695209503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4040074348449707},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33796870708465576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2275679111480713},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1048879325389862},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07190948724746704},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06102606654167175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-75778-5_2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-75778-5_2","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W81140875","https://openalex.org/W1549353711","https://openalex.org/W2145339207","https://openalex.org/W2157174816","https://openalex.org/W2167415375","https://openalex.org/W2257979135","https://openalex.org/W2575705757","https://openalex.org/W2583993537","https://openalex.org/W2766447205","https://openalex.org/W2788781499","https://openalex.org/W2902907165","https://openalex.org/W2907923173","https://openalex.org/W2962295100","https://openalex.org/W2963575966","https://openalex.org/W3018036994","https://openalex.org/W3035170447","https://openalex.org/W3096351713","https://openalex.org/W3100944043","https://openalex.org/W3129322645","https://openalex.org/W3155039249","https://openalex.org/W3194575292","https://openalex.org/W4226197112","https://openalex.org/W4290052206","https://openalex.org/W4311354561","https://openalex.org/W4384069847","https://openalex.org/W6740801417","https://openalex.org/W6832648441"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W1925875298","https://openalex.org/W4292701710"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}