{"id":"https://openalex.org/W1488752568","doi":"https://doi.org/10.1007/978-3-540-30132-5_151","title":"Use of Successful Policies to Relearn for Induced States of Failure in Reinforcement Learning","display_name":"Use of Successful Policies to Relearn for Induced States of Failure in Reinforcement Learning","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W1488752568","doi":"https://doi.org/10.1007/978-3-540-30132-5_151","mag":"1488752568"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-30132-5_151","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-30132-5_151","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5084942408","display_name":"Tadahiko Murata","orcid":"https://orcid.org/0000-0002-1654-3945"},"institutions":[{"id":"https://openalex.org/I56624758","display_name":"Kansai University","ror":"https://ror.org/03xg1f311","country_code":"JP","type":"education","lineage":["https://openalex.org/I56624758"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tadahiko Murata","raw_affiliation_strings":["Faculty of Informatics, Kansai University, 2-1-1 Ryozenji, Takatsuki, 569-1095, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Kansai University, 2-1-1 Ryozenji, Takatsuki, 569-1095, Osaka, Japan","institution_ids":["https://openalex.org/I56624758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101622865","display_name":"Hiroshi Matsumoto","orcid":"https://orcid.org/0000-0002-2984-9329"},"institutions":[{"id":"https://openalex.org/I56624758","display_name":"Kansai University","ror":"https://ror.org/03xg1f311","country_code":"JP","type":"education","lineage":["https://openalex.org/I56624758"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Matsumoto","raw_affiliation_strings":["Faculty of Informatics, Kansai University, 2-1-1 Ryozenji, Takatsuki, 569-1095, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Kansai University, 2-1-1 Ryozenji, Takatsuki, 569-1095, Osaka, Japan","institution_ids":["https://openalex.org/I56624758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07161269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1114","last_page":"1120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9969000220298767,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9753999710083008,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8616073727607727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7810280323028564},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.5279706716537476},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4863317608833313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4780469536781311},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4633871018886566},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4190899431705475},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3406336307525635},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1048479974269867},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0821845531463623},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.07415765523910522},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06261217594146729}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8616073727607727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810280323028564},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.5279706716537476},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4863317608833313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4780469536781311},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4633871018886566},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4190899431705475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3406336307525635},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1048479974269867},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0821845531463623},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.07415765523910522},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06261217594146729},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-540-30132-5_151","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-30132-5_151","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2062126323","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2125055259","https://openalex.org/W2149706766","https://openalex.org/W2322148045","https://openalex.org/W4214717370","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W4384470695","https://openalex.org/W3134840015","https://openalex.org/W4366979180"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}