{"id":"https://openalex.org/W2139474891","doi":"https://doi.org/10.1109/tnn.2004.828760","title":"A New Criterion Using Information Gain for Action Selection Strategy in Reinforcement Learning","display_name":"A New Criterion Using Information Gain for Action Selection Strategy in Reinforcement Learning","publication_year":2004,"publication_date":"2004-07-01","ids":{"openalex":"https://openalex.org/W2139474891","doi":"https://doi.org/10.1109/tnn.2004.828760","mag":"2139474891","pmid":"https://pubmed.ncbi.nlm.nih.gov/15461073"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnn.2004.828760","pdf_url":null,"source":{"id":"https://openalex.org/S42080949","display_name":"IEEE Transactions on Neural Networks","issn_l":"1045-9227","issn":["1045-9227","1941-0093"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/50282/1/01310353.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008161122","display_name":"Kazunori Iwata","orcid":"https://orcid.org/0000-0002-2638-7288"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"funder","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Iwata","raw_affiliation_strings":["[Graduate School of Informatics, Kyoto University, Japan]"],"affiliations":[{"raw_affiliation_string":"[Graduate School of Informatics, Kyoto University, Japan]","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062709079","display_name":"Kazushi Ikeda","orcid":"https://orcid.org/0000-0003-3330-6121"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"funder","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Ikeda","raw_affiliation_strings":["[Graduate School of Informatics, Kyoto University, Japan]"],"affiliations":[{"raw_affiliation_string":"[Graduate School of Informatics, Kyoto University, Japan]","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005166227","display_name":"Hideaki Sakai","orcid":"https://orcid.org/0000-0001-9839-1377"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"funder","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H. Sakai","raw_affiliation_strings":["[Graduate School of Informatics, Kyoto University, Japan]"],"affiliations":[{"raw_affiliation_string":"[Graduate School of Informatics, Kyoto University, Japan]","institution_ids":["https://openalex.org/I22299242"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.451,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":29,"citation_normalized_percentile":{"value":0.929139,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":90},"biblio":{"volume":"15","issue":"4","first_page":"792","last_page":"799"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9996,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9996,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9937,"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/information-gain","display_name":"Information gain","score":0.8400061},{"id":"https://openalex.org/keywords/coding-gain","display_name":"Coding gain","score":0.72629213},{"id":"https://openalex.org/keywords/information-gain-ratio","display_name":"Information gain ratio","score":0.5997088},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5385306},{"id":"https://openalex.org/keywords/information-theory","display_name":"Information Theory","score":0.4689279}],"concepts":[{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.8400061},{"id":"https://openalex.org/C76862118","wikidata":"https://www.wikidata.org/wiki/Q1105671","display_name":"Coding gain","level":3,"score":0.72629213},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.70726943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6563189},{"id":"https://openalex.org/C202185110","wikidata":"https://www.wikidata.org/wiki/Q6031086","display_name":"Information gain ratio","level":3,"score":0.5997088},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5914087},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5385306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.526751},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.4689279},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4669854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4544154},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.44453132},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4163141},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30833465},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25334615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20276752},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14868054},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.13519374},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003661","descriptor_name":"Decision Support Techniques","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007257","descriptor_name":"Information Theory","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011337","descriptor_name":"Probability Learning","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnn.2004.828760","pdf_url":null,"source":{"id":"https://openalex.org/S42080949","display_name":"IEEE Transactions on Neural Networks","issn_l":"1045-9227","issn":["1045-9227","1941-0093"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hdl.handle.net/2433/50282","pdf_url":"https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/50282/1/01310353.pdf","source":{"id":"https://openalex.org/S4306401454","display_name":"Kyoto University Research Information Repository (Kyoto University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I22299242","host_organization_name":"Kyoto University","host_organization_lineage":["https://openalex.org/I22299242"],"host_organization_lineage_names":["Kyoto University"],"type":"repository"},"license":"mit","license_id":"https://openalex.org/licenses/mit","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15461073","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://hdl.handle.net/2433/50282","pdf_url":"https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/50282/1/01310353.pdf","source":{"id":"https://openalex.org/S4306401454","display_name":"Kyoto University Research Information Repository (Kyoto University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I22299242","host_organization_name":"Kyoto University","host_organization_lineage":["https://openalex.org/I22299242"],"host_organization_lineage_names":["Kyoto University"],"type":"repository"},"license":"mit","license_id":"https://openalex.org/licenses/mit","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":20,"referenced_works":["https://openalex.org/W129373126","https://openalex.org/W1522099992","https://openalex.org/W1557517019","https://openalex.org/W1558348055","https://openalex.org/W1591803298","https://openalex.org/W1931792391","https://openalex.org/W1968908999","https://openalex.org/W1994616650","https://openalex.org/W2054658115","https://openalex.org/W2056099894","https://openalex.org/W2106596127","https://openalex.org/W2107726111","https://openalex.org/W2133378540","https://openalex.org/W2142635246","https://openalex.org/W2150339816","https://openalex.org/W2531891978","https://openalex.org/W32403112","https://openalex.org/W4214717370","https://openalex.org/W4302033506","https://openalex.org/W63231299"],"related_works":["https://openalex.org/W4312502896","https://openalex.org/W2784382611","https://openalex.org/W2771317484","https://openalex.org/W2622082079","https://openalex.org/W2367932743","https://openalex.org/W2367616228","https://openalex.org/W2348174691","https://openalex.org/W2139474891","https://openalex.org/W1986366279","https://openalex.org/W1544163028"],"abstract_inverted_index":{"In":[0,90],"this":[1],"paper,":[2],"we":[3,34,67,93],"regard":[4],"the":[5,17,20,24,27,32,41,60,64,69,104],"sequence":[6],"of":[7,23,29,59,73],"returns":[8],"as":[9,79],"outputs":[10],"from":[11],"a":[12,56,80],"parametric":[13],"compound":[14],"source.":[15],"Utilizing":[16],"fact":[18],"that":[19,95],"coding":[21,43],"rate":[22],"source":[25],"shows":[26],"amount":[28],"information":[30,49,53,61,65,77],"about":[31],"return,":[33],"describe":[35],"/spl":[36,71,97],"lscr/-learning":[37],"algorithms":[38],"based":[39],"on":[40],"predictive":[42],"idea":[44],"for":[45],"estimating":[46],"an":[47],"expected":[48],"gain":[50,78],"concerning":[51],"future":[52],"and":[54],"give":[55],"convergence":[57],"proof":[58],"gain.":[62],"Using":[63],"gain,":[66],"propose":[68],"ratio":[70],"omega/":[72],"return":[74],"loss":[75],"to":[76,83],"new":[81],"criterion":[82],"be":[84],"used":[85],"in":[86],"probabilistic":[87],"action-selection":[88],"strategies.":[89],"experimental":[91],"results,":[92],"found":[94],"our":[96],"omega/-based":[98],"strategy":[99],"performs":[100],"well":[101],"compared":[102],"with":[103],"conventional":[105],"Q-based":[106],"strategy.":[107]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2139474891","counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-04-05T22:06:17.483523","created_date":"2016-06-24"}