{"id":"https://openalex.org/W4213157992","doi":"https://doi.org/10.5220/0010786600003116","title":"Safe Policy Improvement Approaches on Discrete Markov Decision Processes","display_name":"Safe Policy Improvement Approaches on Discrete Markov Decision Processes","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4213157992","doi":"https://doi.org/10.5220/0010786600003116"},"language":"en","primary_location":{"id":"doi:10.5220/0010786600003116","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010786600003116","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 14th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.5220/0010786600003116","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091846317","display_name":"Philipp Scholl","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"]},{"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":"Philipp Scholl","raw_affiliation_strings":["Department of Mathematics, Ludwig-Maximilian-University of Munich, Munich, Germany, --- Select a Country ---","Learning Systems, Siemens Technology, Munich, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Ludwig-Maximilian-University of Munich, Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Learning Systems, Siemens Technology, Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065128348","display_name":"Felix Dietrich","orcid":"https://orcid.org/0000-0002-2906-1769"},"institutions":[{"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":"Felix Dietrich","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008424292","display_name":"Clemens Otte","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":"Clemens Otte","raw_affiliation_strings":["Learning Systems, Siemens Technology, Munich, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning Systems, Siemens Technology, Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"last","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":["Learning Systems, Siemens Technology, Munich, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning Systems, Siemens Technology, Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I1325886976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3113,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47410549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"142","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9850999712944031,"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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9848999977111816,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8105890154838562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6890038251876831},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6449282169342041},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.5216360688209534},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.520881175994873},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.48794740438461304},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47367197275161743},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4655066132545471},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4521397352218628},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.43595170974731445},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42552411556243896},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.42032909393310547},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33439648151397705},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.327436625957489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3101840019226074},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20243045687675476},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.11353716254234314},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07756116986274719}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8105890154838562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6890038251876831},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6449282169342041},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.5216360688209534},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.520881175994873},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.48794740438461304},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47367197275161743},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4655066132545471},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4521397352218628},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.43595170974731445},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42552411556243896},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.42032909393310547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33439648151397705},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.327436625957489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3101840019226074},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20243045687675476},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.11353716254234314},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07756116986274719},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0010786600003116","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010786600003116","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 14th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.12175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.12175","pdf_url":"https://arxiv.org/pdf/2201.12175","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:10.5220/0010786600003116","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010786600003116","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 14th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W580164506","https://openalex.org/W1505937442","https://openalex.org/W1551424636","https://openalex.org/W1576516403","https://openalex.org/W1845972764","https://openalex.org/W2006278461","https://openalex.org/W2121506959","https://openalex.org/W2127470768","https://openalex.org/W2151702863","https://openalex.org/W2169186423","https://openalex.org/W2904453761","https://openalex.org/W2963044034","https://openalex.org/W2963836326","https://openalex.org/W3022566517","https://openalex.org/W3037134744","https://openalex.org/W3093206925","https://openalex.org/W3094261094","https://openalex.org/W3112951354","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2953205341","https://openalex.org/W235065745","https://openalex.org/W2029935773","https://openalex.org/W2787754950","https://openalex.org/W1572215850","https://openalex.org/W1985775355","https://openalex.org/W2352115286","https://openalex.org/W2084793300","https://openalex.org/W2476350415","https://openalex.org/W599377045"],"abstract_inverted_index":{"Safe":[0],"Policy":[1],"Improvement":[2],"(SPI)":[3],"aims":[4],"at":[5,13],"provable":[6],"guarantees":[7],"that":[8,51,67,110],"a":[9,19,43,48,64,87,115],"learned":[10],"policy":[11],"is":[12,52,120],"least":[14],"approximately":[15],"as":[16,18,114],"good":[17,131],"given":[20],"baseline":[21],"policy.":[22],"Building":[23],"on":[24,55,80,117],"SPI":[25,78,90,102],"with":[26],"Soft":[27],"Baseline":[28],"Bootstrapping":[29],"(Soft-SPIBB)":[30],"by":[31],"Nadjahi":[32],"et":[33],"al.,":[34],"we":[35,62,85],"identify":[36],"theoretical":[37],"issues":[38],"in":[39],"their":[40],"approach,":[41],"provide":[42,63],"corrected":[44],"theory,":[45],"and":[46,92,133],"derive":[47],"new":[49],"algorithm":[50,66],"provably":[53],"safe":[54],"finite":[56],"Markov":[57],"Decision":[58],"Processes":[59],"(MDP).":[60],"Additionally,":[61],"heuristic":[65],"exhibits":[68],"the":[69,76,105,112,118,124],"best":[70],"performance":[71,107],"among":[72],"many":[73],"state":[74],"of":[75,89,98,101,108,126],"art":[77],"algorithms":[79,91,109],"two":[81,99],"different":[82],"benchmarks.":[83],"Furthermore,":[84],"introduce":[86],"taxonomy":[88],"empirically":[93],"show":[94],"an":[95],"interesting":[96],"property":[97],"classes":[100],"algorithms:":[103],"while":[104],"mean":[106],"incorporate":[111],"uncertainty":[113],"penalty":[116],"action-value":[119],"higher,":[121],"actively":[122],"restricting":[123],"set":[125],"policies":[127,132],"more":[128],"consistently":[129],"produces":[130],"is,":[134],"thus,":[135],"safer.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}