{"id":"https://openalex.org/W3009923408","doi":"https://doi.org/10.1145/3380688.3380706","title":"A Sublinear-Regret Reinforcement Learning Algorithm on Constrained Markov Decision Processes with reset action","display_name":"A Sublinear-Regret Reinforcement Learning Algorithm on Constrained Markov Decision Processes with reset action","publication_year":2020,"publication_date":"2020-01-17","ids":{"openalex":"https://openalex.org/W3009923408","doi":"https://doi.org/10.1145/3380688.3380706","mag":"3009923408"},"language":"en","primary_location":{"id":"doi:10.1145/3380688.3380706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3380688.3380706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Machine Learning and Soft Computing","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/A5046987979","display_name":"Takashi Watanabe","orcid":"https://orcid.org/0000-0002-3227-9048"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takashi Watanabe","raw_affiliation_strings":["Kyoto University, Graduate school of Human and Environmental Studies, Kyoto city, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Graduate school of Human and Environmental Studies, Kyoto city, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018117923","display_name":"Takashi Sakuragawa","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Sakuragawa","raw_affiliation_strings":["Kyoto University, Graduate school of Human and Environmental Studies, Kyoto city, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Graduate school of Human and Environmental Studies, Kyoto city, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046987979"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02214871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9948999881744385,"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":0.9948999881744385,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.934499979019165,"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/regret","display_name":"Regret","score":0.9017298221588135},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8479223251342773},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.8043804168701172},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8025259375572205},{"id":"https://openalex.org/keywords/reset","display_name":"Reset (finance)","score":0.704474925994873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5886764526367188},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5416659712791443},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5399773716926575},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4838027358055115},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.465247243642807},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4540941119194031},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4391842484474182},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3852667212486267},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3220362663269043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24802210927009583},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19377759099006653},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.135797381401062},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09711086750030518}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9017298221588135},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8479223251342773},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.8043804168701172},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8025259375572205},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.704474925994873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5886764526367188},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5416659712791443},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5399773716926575},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4838027358055115},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.465247243642807},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4540941119194031},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4391842484474182},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3852667212486267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3220362663269043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24802210927009583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19377759099006653},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.135797381401062},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09711086750030518},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3380688.3380706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3380688.3380706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Machine Learning and Soft Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W646387458","https://openalex.org/W1518931405","https://openalex.org/W1850488217","https://openalex.org/W1999678910","https://openalex.org/W2119567691","https://openalex.org/W2947782105"],"related_works":["https://openalex.org/W3039767703","https://openalex.org/W4287863949","https://openalex.org/W4287102143","https://openalex.org/W1850488217","https://openalex.org/W2945119207","https://openalex.org/W3182614517","https://openalex.org/W2808418668","https://openalex.org/W2970347269","https://openalex.org/W2357975469","https://openalex.org/W2101748387"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"study":[4],"model-based":[5],"reinforcement":[6],"learning":[7],"in":[8],"an":[9,21],"unknown":[10],"constrained":[11],"Markov":[12],"Decision":[13],"Processes":[14],"(CMDPs)":[15],"with":[16,57],"reset":[17],"action.":[18],"We":[19,44],"propose":[20],"algorithm,":[22],"Constrained-UCRL,":[23],"which":[24],"uses":[25],"confidence":[26],"interval":[27],"like":[28],"UCRL2,":[29],"and":[30,64],"solves":[31],"linear":[32],"programming":[33],"problem":[34],"to":[35,54],"compute":[36],"policy":[37],"at":[38],"the":[39,62,65],"start":[40],"of":[41],"each":[42],"episode.":[43],"show":[45],"that":[46],"Constrained-UCRL":[47],"achieves":[48],"sublinear":[49],"regret":[50],"bounds":[51],"\u00d5(SA1/2T3/4)":[52],"up":[53],"logarithmic":[55],"factors":[56],"high":[58],"probability":[59],"for":[60],"both":[61],"gain":[63],"constraint":[66],"violations.":[67]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}