{"id":"https://openalex.org/W2572301868","doi":"https://doi.org/10.3233/978-1-61499-720-7-145","title":"Accelerating Reinforcement Learning by Mirror Images","display_name":"Accelerating Reinforcement Learning by Mirror Images","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2572301868","doi":"https://doi.org/10.3233/978-1-61499-720-7-145","mag":"2572301868"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-720-7-145","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-720-7-145","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","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/A5064221662","display_name":"Kitao Takehiro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kitao Takehiro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Miura Takao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miura Takao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.01875232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7300999760627747,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7300999760627747,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.666700005531311,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.6018000245094299,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/mathematics","display_name":"Mathematics","score":0.7430272102355957},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5532801747322083},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.5129796862602234},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5064488649368286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2951013743877411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.1860421895980835},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09262284636497498},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.04380497336387634}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7430272102355957},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5532801747322083},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.5129796862602234},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5064488649368286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2951013743877411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.1860421895980835},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09262284636497498},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.04380497336387634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/978-1-61499-720-7-145","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-720-7-145","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W2007980826","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2061531152","https://openalex.org/W3002753104"],"abstract_inverted_index":{"In":[0,40],"this":[1,41],"investigation,":[2,42],"we":[3,43,69],"propose":[4],"how":[5],"to":[6,36,76],"accelerate":[7,37],"Q-learning":[8,38,45],"which":[9],"is":[10],"one":[11,81],"of":[12,30],"the":[13,72,77,80],"most":[14],"successful":[15],"reinforcement":[16],"learning":[17],"methods":[18],"using":[19],"mirror":[20,84],"images":[21,26],"for":[22],"hunting":[23],"problems.":[24],"Mirror":[25],"have":[27],"symmetric":[28],"differences":[29],"views,":[31],"and":[32],"they":[33],"allow":[34],"us":[35],"dramatically.":[39],"show":[44],"goes":[46],"2":[47],"times":[48,54],"faster":[49,55],"(one":[50],"mirror)":[51],"or":[52],"3":[53],"(2":[56],"mirrors)":[57],"but":[58],"a":[59],"capturing":[60],"ability":[61],"decreased":[62],"slightly":[63],"even":[64],"if":[65,79],"intervention":[66],"happens.":[67],"Moreover,":[68],"prove":[70],"that":[71],"new":[73],"approach":[74],"gets":[75],"convergence":[78],"with":[82],"no":[83],"does.":[85]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}