{"id":"https://openalex.org/W2282802439","doi":"https://doi.org/10.1109/gcce.2015.7398723","title":"Multi-task reinforcement learning with associative memory models considering the multiple distributions of MDPs","display_name":"Multi-task reinforcement learning with associative memory models considering the multiple distributions of MDPs","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2282802439","doi":"https://doi.org/10.1109/gcce.2015.7398723","mag":"2282802439"},"language":"en","primary_location":{"id":"doi:10.1109/gcce.2015.7398723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce.2015.7398723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 4th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"},"type":"article","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/A5017025854","display_name":"Kinbara Fumihiro","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kinbara Fumihiro","raw_affiliation_strings":["Dept. of Computer Science and Engineering, Nagoya Institute of Technology Gokiso-cho, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, Nagoya Institute of Technology Gokiso-cho, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088832778","display_name":"Sh\u014dhei Kato","orcid":"https://orcid.org/0000-0003-4130-2729"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shohei Kato","raw_affiliation_strings":["Dept. of Computer Science and Engineering, Nagoya Institute of Technology Gokiso-cho, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, Nagoya Institute of Technology Gokiso-cho, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113738409","display_name":"Munehiro Nakamura","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Munehiro Nakamura","raw_affiliation_strings":["Dept. of Computer Science and Engineering, Nagoya Institute of Technology Gokiso-cho, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, Nagoya Institute of Technology Gokiso-cho, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017025854"],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":0.4314,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77792741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"27","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9983000159263611,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.928336501121521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7783728837966919},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7582731246948242},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.6077343225479126},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.593957781791687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5375629663467407},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3823986351490021},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09299740195274353}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.928336501121521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783728837966919},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7582731246948242},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.6077343225479126},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.593957781791687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5375629663467407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3823986351490021},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09299740195274353},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce.2015.7398723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce.2015.7398723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 4th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2006327398","https://openalex.org/W2097381042","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2145983895","https://openalex.org/W4214717370","https://openalex.org/W6674600207"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2086122291","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W1982127714"],"abstract_inverted_index":{"Multi-task":[0],"reinforcement":[1,10,19,90],"learning":[2,11,20,91],"is":[3],"one":[4],"of":[5,16,33,57,70],"the":[6,14,17,34,43,59],"promising":[7],"approaches":[8],"in":[9,25],"problems.":[12,51],"While":[13],"formulation":[15,44,60],"multi-task":[18,89],"problem":[21,65],"have":[22],"been":[23,37],"established":[24],"a":[26,30,55,62],"previous":[27],"study,":[28],"only":[29],"single":[31],"distribution":[32],"tasks":[35],"has":[36],"considered.":[38],"However,":[39],"we":[40,74],"assume":[41],"that":[42],"can":[45],"hardly":[46],"be":[47],"applied":[48],"to":[49,61,86],"real-world":[50],"This":[52],"paper":[53],"presents":[54],"method":[56],"expanding":[58],"more":[63],"general":[64],"by":[66],"considering":[67],"multiple":[68],"distributions":[69],"tasks.":[71],"In":[72],"addition,":[73],"propose":[75],"an":[76,87],"agent":[77],"model":[78],"with":[79],"associative":[80],"memory":[81],"models,":[82],"then":[83],"apply":[84],"it":[85],"expanded":[88],"problem.":[92]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}