{"id":"https://openalex.org/W2402677255","doi":null,"title":"Probability Redistribution using Time Hopping for Reinforcement Learning","display_name":"Probability Redistribution using Time Hopping for Reinforcement Learning","publication_year":2009,"publication_date":"2009-08-17","ids":{"openalex":"https://openalex.org/W2402677255","mag":"2402677255"},"language":"en","primary_location":{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/26089","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/26089","pdf_url":"http://hdl.handle.net/10044/1/26089","source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"10th International Symposium on Advanced Intelligent Systems, ISIS 2009","raw_type":"Conference Paper"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10044/1/26089","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036281885","display_name":"Petar S. Kormushev","orcid":"https://orcid.org/0000-0002-6677-3044","observed_orcids":["https://orcid.org/0000-0002-6677-3044"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petar Kormushev","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6677-3044","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109308961","display_name":"Fangyan Dong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangyan Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066941401","display_name":"Kaoru Hirota","orcid":"https://orcid.org/0000-0001-5347-6182","observed_orcids":["https://orcid.org/0000-0001-5347-6182"]},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698","https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaoru Hirota","raw_affiliation_strings":["Tokyo Institute of Technology;"],"raw_orcid":"https://orcid.org/0000-0001-5347-6182","affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology;","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2494,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36486666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.0,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/time-hopping","display_name":"time hopping","score":0.9150000214576721},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7900000214576721},{"id":"https://openalex.org/keywords/exploration-efficiency","display_name":"exploration efficiency","score":0.9700000286102295},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8029999732971191}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7775838375091553},{"id":"https://openalex.org/C74080474","wikidata":"https://www.wikidata.org/wiki/Q7305975","display_name":"Redistribution (election)","level":3,"score":0.5959619879722595},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.5599098205566406},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5595619678497314},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5565090179443359},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.555047333240509},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47800031304359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44987383484840393},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.43287983536720276},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.41798311471939087},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3300132751464844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27053385972976685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.268171489238739},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13941895961761475},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1353588104248047},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/26089","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/26089","pdf_url":"http://hdl.handle.net/10044/1/26089","source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"10th International Symposium on Advanced Intelligent Systems, ISIS 2009","raw_type":"Conference Paper"},{"id":"mag:2402677255","doi":null,"is_oa":false,"landing_page_url":"http://kormushev.com/papers/Kormushev_ISIS-2009.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/26089","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/26089","pdf_url":"http://hdl.handle.net/10044/1/26089","source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"10th International Symposium on Advanced Intelligent Systems, ISIS 2009","raw_type":"Conference Paper"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2402677255.pdf","grobid_xml":"https://content.openalex.org/works/W2402677255.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W51508254","https://openalex.org/W1480676279","https://openalex.org/W1503697431","https://openalex.org/W1504212531","https://openalex.org/W1575130825","https://openalex.org/W1594783240","https://openalex.org/W1600046456","https://openalex.org/W1680254737","https://openalex.org/W1917339001","https://openalex.org/W1927790226","https://openalex.org/W1965227651","https://openalex.org/W1996625075","https://openalex.org/W2038301401","https://openalex.org/W2052117683","https://openalex.org/W2072492557","https://openalex.org/W2100677568","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2135043890","https://openalex.org/W2139053308","https://openalex.org/W2161395589","https://openalex.org/W2169209873","https://openalex.org/W2172968643","https://openalex.org/W2215936659","https://openalex.org/W2489939061","https://openalex.org/W2521075165","https://openalex.org/W3023407077"],"related_works":["https://openalex.org/W7014732757","https://openalex.org/W2963175734","https://openalex.org/W74030516","https://openalex.org/W7171660536","https://openalex.org/W1927790226","https://openalex.org/W1680254737","https://openalex.org/W6960192650","https://openalex.org/W7154726158","https://openalex.org/W2911139728","https://openalex.org/W3034648475"],"abstract_inverted_index":{"\u2014A":[0],"method":[1,64],"for":[2,11],"using":[3],"the":[4,28,33,45,63,66,71],"Time":[5,50],"Hopping":[6,51],"technique":[7],"as":[8,38],"a":[9,21,55],"tool":[10],"probability":[12,30,73],"redistribution":[13],"is":[14,24,41],"proposed.":[15],"Applied":[16],"to":[17,26,75],"reinforcement":[18,58],"learning":[19,59],"in":[20],"simulation,":[22],"it":[23],"able":[25],"re-shape":[27],"state":[29,72],"distribution":[31,74],"of":[32,49],"underlying":[34],"Markov":[35],"decision":[36],"process":[37],"desired.":[39],"This":[40],"achieved":[42],"by":[43,69],"modifying":[44],"target":[46],"selection":[47],"strategy":[48],"appropriately.":[52],"Experiments":[53],"with":[54],"robot":[56],"maze":[57],"problem":[60],"show":[61],"that":[62],"improves":[65],"exploration":[67],"efficiency":[68],"re-shaping":[70],"an":[76],"almost":[77],"uniform":[78],"distribution.":[79]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}