{"id":"https://openalex.org/W4385767815","doi":"https://doi.org/10.24963/ijcai.2023/608","title":"A Rigorous Risk-aware Linear Approach to Extended Markov Ratio Decision Processes with Embedded Learning","display_name":"A Rigorous Risk-aware Linear Approach to Extended Markov Ratio Decision Processes with Embedded Learning","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767815","doi":"https://doi.org/10.24963/ijcai.2023/608"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/608","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/608","pdf_url":"https://www.ijcai.org/proceedings/2023/0608.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0608.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090890409","display_name":"Alexander Zadorojniy","orcid":"https://orcid.org/0000-0002-8121-5913"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Alexander Zadorojniy","raw_affiliation_strings":["IBM Research - Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025629651","display_name":"Takayuki Osogami","orcid":"https://orcid.org/0000-0001-8748-5706"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takayuki Osogami","raw_affiliation_strings":["IBM Research - Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091822383","display_name":"Orit Davidovich","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Orit Davidovich","raw_affiliation_strings":["IBM Research - Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Israel","institution_ids":["https://openalex.org/I4210167297"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09318908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5475","last_page":"5483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9876000285148621,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9832000136375427,"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":0.7854235172271729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6725513935089111},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6655353903770447},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6374355554580688},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5643861889839172},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5592197775840759},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.43362191319465637},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41748321056365967},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4128107726573944},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4081155061721802},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28389328718185425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24646583199501038},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24173492193222046}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7854235172271729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6725513935089111},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6655353903770447},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6374355554580688},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5643861889839172},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5592197775840759},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.43362191319465637},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41748321056365967},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4128107726573944},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4081155061721802},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28389328718185425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24646583199501038},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24173492193222046},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/608","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/608","pdf_url":"https://www.ijcai.org/proceedings/2023/0608.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/608","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/608","pdf_url":"https://www.ijcai.org/proceedings/2023/0608.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767815.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W580164506","https://openalex.org/W1518931405","https://openalex.org/W1970573563","https://openalex.org/W1984901446","https://openalex.org/W2021298813","https://openalex.org/W2031259314","https://openalex.org/W2033040247","https://openalex.org/W2040228279","https://openalex.org/W2045961034","https://openalex.org/W2054110366","https://openalex.org/W2082815106","https://openalex.org/W2128347943","https://openalex.org/W2141076336","https://openalex.org/W2141252092","https://openalex.org/W2146835059","https://openalex.org/W2167471538","https://openalex.org/W2569529055","https://openalex.org/W2963334929","https://openalex.org/W2984671888","https://openalex.org/W3021764208","https://openalex.org/W3045055178","https://openalex.org/W3047066292","https://openalex.org/W4283796290","https://openalex.org/W4295830359","https://openalex.org/W4298023569","https://openalex.org/W4301621763","https://openalex.org/W4301808069"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2315999538","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"We":[0,13,36,70,91,112],"consider":[1],"the":[2,42,63],"problem":[3],"of":[4,86,106],"risk-aware":[5],"Markov":[6,19],"Decision":[7,21],"Processes":[8,22],"(MDPs)":[9],"for":[10,45],"Safe":[11],"AI.":[12],"introduce":[14],"a":[15,51,76],"theoretical":[16,48],"framework,":[17],"Extended":[18],"Ratio":[20],"(EMRDP),":[23],"that":[24],"incorporates":[25],"risk":[26],"into":[27,33],"MDPs":[28],"and":[29,65,88],"embeds":[30],"environment":[31],"learning":[32],"this":[34,55],"framework.":[35],"propose":[37],"an":[38],"algorithm":[39,56,73],"to":[40,96,118],"find":[41,92],"optimal":[43],"policy":[44],"EMRDP":[46],"with":[47,109],"guarantees.":[49],"Under":[50],"certain":[52],"monotonicity":[53],"assumption,":[54],"runs":[57],"in":[58,62],"strongly-polynomial":[59],"time":[60],"both":[61],"discounted":[64],"expected":[66],"average":[67],"reward":[68],"models.":[69],"validate":[71],"our":[72],"empirically":[74],"on":[75],"Grid":[77],"World":[78],"benchmark,":[79],"evaluating":[80],"its":[81,93,103,114],"solution":[82,94],"quality,":[83],"required":[84,104],"number":[85,105],"steps,":[87],"numerical":[89,115],"stability.":[90],"quality":[95],"be":[97],"stable":[98],"under":[99],"data":[100],"noising,":[101],"while":[102],"steps":[107],"grows":[108],"added":[110],"noise.":[111],"observe":[113],"stability":[116],"compared":[117],"global":[119],"methods.":[120]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}