{"id":"https://openalex.org/W4385764185","doi":"https://doi.org/10.24963/ijcai.2023/413","title":"Autonomous Exploration for Navigating in MDPs Using Blackbox RL Algorithms","display_name":"Autonomous Exploration for Navigating in MDPs Using Blackbox RL Algorithms","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764185","doi":"https://doi.org/10.24963/ijcai.2023/413"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/413","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/413","pdf_url":"https://www.ijcai.org/proceedings/2023/0413.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0413.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004854778","display_name":"Pratik Gajane","orcid":"https://orcid.org/0000-0002-8087-5661"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Pratik Gajane","raw_affiliation_strings":["Eindhoven University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073954294","display_name":"Peter Auer","orcid":"https://orcid.org/0000-0001-8385-9635"},"institutions":[{"id":"https://openalex.org/I182712176","display_name":"Montanuniversit\u00e4t Leoben","ror":"https://ror.org/02fhfw393","country_code":"AT","type":"education","lineage":["https://openalex.org/I182712176"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Peter Auer","raw_affiliation_strings":["Montanuniversitat Leoben"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montanuniversitat Leoben","institution_ids":["https://openalex.org/I182712176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031149136","display_name":"Ronald Ortner","orcid":"https://orcid.org/0000-0001-6033-2208"},"institutions":[{"id":"https://openalex.org/I182712176","display_name":"Montanuniversit\u00e4t Leoben","ror":"https://ror.org/02fhfw393","country_code":"AT","type":"education","lineage":["https://openalex.org/I182712176"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ronald Ortner","raw_affiliation_strings":["Montanuniversitat Leoben"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montanuniversitat Leoben","institution_ids":["https://openalex.org/I182712176"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3714","last_page":"3722"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8586264848709106},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.8500572443008423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7450850009918213},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7236799597740173},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.693095326423645},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6300918459892273},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.597848653793335},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5279718041419983},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.502781867980957},{"id":"https://openalex.org/keywords/online-algorithm","display_name":"Online algorithm","score":0.4834654927253723},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47993022203445435},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.458435595035553},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.42822009325027466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2402067482471466},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23199498653411865},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1590595245361328}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8586264848709106},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8500572443008423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7450850009918213},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7236799597740173},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.693095326423645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6300918459892273},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.597848653793335},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5279718041419983},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.502781867980957},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.4834654927253723},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47993022203445435},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.458435595035553},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42822009325027466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2402067482471466},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23199498653411865},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1590595245361328},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/413","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/413","pdf_url":"https://www.ijcai.org/proceedings/2023/0413.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.2023/413","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/413","pdf_url":"https://www.ijcai.org/proceedings/2023/0413.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":[{"score":0.75,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G8456453420","display_name":"Reinforcement Learning: Beyond Optimality","funder_award_id":"TAI 590","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"}],"funders":[{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764185.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1562462135","https://openalex.org/W1590585250","https://openalex.org/W1662803991","https://openalex.org/W1850488217","https://openalex.org/W1979711143","https://openalex.org/W1999678910","https://openalex.org/W2000514530","https://openalex.org/W2013830186","https://openalex.org/W2034806191","https://openalex.org/W2105828468","https://openalex.org/W2139612737","https://openalex.org/W2160589914","https://openalex.org/W2164424353","https://openalex.org/W2293729149","https://openalex.org/W2596982695","https://openalex.org/W2614839826","https://openalex.org/W2616430965","https://openalex.org/W2788093588","https://openalex.org/W2885550588","https://openalex.org/W2896027395","https://openalex.org/W2902298341","https://openalex.org/W2914261249","https://openalex.org/W2963523627","https://openalex.org/W2980964291","https://openalex.org/W2993386228","https://openalex.org/W3020125231","https://openalex.org/W3035599863","https://openalex.org/W3041070598","https://openalex.org/W3043114440","https://openalex.org/W3099009443","https://openalex.org/W3129322645","https://openalex.org/W4281484278","https://openalex.org/W4287725108","https://openalex.org/W4287975440","https://openalex.org/W4292022450","https://openalex.org/W4297804636","https://openalex.org/W4300971780","https://openalex.org/W6635207764","https://openalex.org/W6650587873","https://openalex.org/W6675490775","https://openalex.org/W6734097942"],"related_works":["https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W1850488217","https://openalex.org/W4287102143","https://openalex.org/W2945119207","https://openalex.org/W3182614517","https://openalex.org/W2097562045","https://openalex.org/W2963049774","https://openalex.org/W2572248225","https://openalex.org/W2952412049"],"abstract_inverted_index":{"We":[0,48,84],"consider":[1],"the":[2,22,31,75,90,99,103,115],"problem":[3],"of":[4,40,77,93,98,102,117,122],"navigating":[5],"in":[6,96],"a":[7,37,45,50,66,71,81],"Markov":[8],"decision":[9],"process":[10],"where":[11],"extrinsic":[12],"rewards":[13],"are":[14,34],"either":[15],"absent":[16],"or":[17],"ignored.":[18],"In":[19],"this":[20],"setting,":[21],"objective":[23],"is":[24],"to":[25,28,80,113],"learn":[26],"policies":[27],"reach":[29],"all":[30],"states":[32],"that":[33],"reachable":[35],"within":[36],"given":[38],"number":[39],"steps":[41],"(in":[42],"expectation)":[43],"from":[44],"starting":[46],"state.":[47],"introduce":[49],"novel":[51],"meta-algorithm":[52],"which":[53],"can":[54],"use":[55],"any":[56],"online":[57,78],"reinforcement":[58],"learning":[59],"algorithm":[60,69,95,119],"(with":[61],"appropriate":[62],"regret":[63,100],"guarantees)":[64],"as":[65],"black-box.":[67],"Our":[68],"demonstrates":[70],"method":[72],"for":[73],"transforming":[74],"output":[76],"algorithms":[79],"batch":[82],"setting.":[83],"prove":[85],"an":[86],"upper":[87],"bound":[88,101],"on":[89],"sample":[91],"complexity":[92],"our":[94,118,123],"terms":[97],"used":[104],"black-box":[105],"RL":[106],"algorithm.":[107],"Furthermore,":[108],"we":[109],"provide":[110],"experimental":[111],"results":[112],"validate":[114],"effectiveness":[116],"and":[120],"correctness":[121],"theoretical":[124],"results.":[125]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}