{"id":"https://openalex.org/W2051454552","doi":"https://doi.org/10.2991/icassr-14.2014.27","title":"Modified Reinforcement Learning Infrastructure","display_name":"Modified Reinforcement Learning Infrastructure","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2051454552","doi":"https://doi.org/10.2991/icassr-14.2014.27","mag":"2051454552"},"language":"en","primary_location":{"id":"doi:10.2991/icassr-14.2014.27","doi":"https://doi.org/10.2991/icassr-14.2014.27","is_oa":true,"landing_page_url":"https://doi.org/10.2991/icassr-14.2014.27","pdf_url":"https://www.atlantis-press.com/article/13570.pdf","source":{"id":"https://openalex.org/S4220651947","display_name":"Advances in intelligent systems research/Advances in Intelligent Systems Research","issn_l":"1951-6851","issn":["1951-6851","2731-7870"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310315540","host_organization_name":"Atlantis Press","host_organization_lineage":["https://openalex.org/P4310315540"],"host_organization_lineage_names":["Atlantis Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Intelligent Systems Research","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.atlantis-press.com/article/13570.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056204857","display_name":"Jyrki Suomala","orcid":"https://orcid.org/0000-0001-7953-5056","observed_orcids":["https://orcid.org/0000-0001-7953-5056"]},"institutions":[{"id":"https://openalex.org/I5188418","display_name":"Laurea University of Applied Sciences","ror":"https://ror.org/05h664633","country_code":"FI","type":"education","lineage":["https://openalex.org/I5188418"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Jyrki Suomala","raw_affiliation_strings":["NeuroLab , Laurea University of Applied Sciences , Vanha maantie 9 , FI-02650 , Espoo , FINLAND","Laurea University of Applied Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NeuroLab , Laurea University of Applied Sciences , Vanha maantie 9 , FI-02650 , Espoo , FINLAND","institution_ids":["https://openalex.org/I5188418"]},{"raw_affiliation_string":"Laurea University of Applied Sciences","institution_ids":["https://openalex.org/I5188418"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045010137","display_name":"Ville Suomala","orcid":"https://orcid.org/0000-0002-3381-5260","observed_orcids":["https://orcid.org/0000-0002-3381-5260"]},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Suomala","raw_affiliation_strings":["University of Oulu , FINLAND","University of Oulu , P.O Box 3000 , FI-90014 ,","University of Oulu, P.O Box 3000, FI-90014, University of Oulu, FINLAND"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oulu , FINLAND","institution_ids":["https://openalex.org/I98381234"]},{"raw_affiliation_string":"University of Oulu , P.O Box 3000 , FI-90014 ,","institution_ids":["https://openalex.org/I98381234"]},{"raw_affiliation_string":"University of Oulu, P.O Box 3000, FI-90014, University of Oulu, FINLAND","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056204857"],"corresponding_institution_ids":["https://openalex.org/I5188418"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.11846462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"104","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-action-spaces","display_name":"large action spaces","score":0.6800000071525574},{"id":"https://openalex.org/keywords/large-state-spaces","display_name":"large state spaces","score":0.8769999742507935},{"id":"https://openalex.org/keywords/consumer-behavior","display_name":"consumer behavior","score":0.8289999961853027},{"id":"https://openalex.org/keywords/retail-environment","display_name":"retail environment","score":0.6779999732971191},{"id":"https://openalex.org/keywords/learning-agents","display_name":"learning agents","score":0.35899999737739563}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.899596095085144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7149379849433899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6021292209625244},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.496891051530838},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4639565348625183},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4463111162185669},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44258615374565125},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41315364837646484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3689573109149933},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11718392372131348},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11269646883010864},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.2991/icassr-14.2014.27","doi":"https://doi.org/10.2991/icassr-14.2014.27","is_oa":true,"landing_page_url":"https://doi.org/10.2991/icassr-14.2014.27","pdf_url":"https://www.atlantis-press.com/article/13570.pdf","source":{"id":"https://openalex.org/S4220651947","display_name":"Advances in intelligent systems research/Advances in Intelligent Systems Research","issn_l":"1951-6851","issn":["1951-6851","2731-7870"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310315540","host_organization_name":"Atlantis Press","host_organization_lineage":["https://openalex.org/P4310315540"],"host_organization_lineage_names":["Atlantis Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Intelligent Systems Research","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.852.9644","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.852.9644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://atlantis-press.com/php/download_paper.php?id%3D13570","raw_type":"text"},{"id":"pmh:oai:www.theseus.fi:10024/344415","doi":null,"is_oa":true,"landing_page_url":"http://www.theseus.fi/handle/10024/344415","pdf_url":null,"source":{"id":"https://openalex.org/S4306400928","display_name":"Theseus (Ammattikorkeakoulujen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"publication"}],"best_oa_location":{"id":"doi:10.2991/icassr-14.2014.27","doi":"https://doi.org/10.2991/icassr-14.2014.27","is_oa":true,"landing_page_url":"https://doi.org/10.2991/icassr-14.2014.27","pdf_url":"https://www.atlantis-press.com/article/13570.pdf","source":{"id":"https://openalex.org/S4220651947","display_name":"Advances in intelligent systems research/Advances in Intelligent Systems Research","issn_l":"1951-6851","issn":["1951-6851","2731-7870"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310315540","host_organization_name":"Atlantis Press","host_organization_lineage":["https://openalex.org/P4310315540"],"host_organization_lineage_names":["Atlantis Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Intelligent Systems Research","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2051454552.pdf","grobid_xml":"https://content.openalex.org/works/W2051454552.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1597739853","https://openalex.org/W1605881095","https://openalex.org/W1977343123","https://openalex.org/W1993665893","https://openalex.org/W2004014356","https://openalex.org/W2071302132","https://openalex.org/W2113122939","https://openalex.org/W2117277172","https://openalex.org/W2117726420","https://openalex.org/W2127469248","https://openalex.org/W2137583503","https://openalex.org/W2149774750","https://openalex.org/W2165368112","https://openalex.org/W2169429092","https://openalex.org/W2326588846","https://openalex.org/W2395238965","https://openalex.org/W3115911361","https://openalex.org/W3150706175"],"related_works":["https://openalex.org/W4297809235","https://openalex.org/W7096522053","https://openalex.org/W21657860","https://openalex.org/W3173549437","https://openalex.org/W4292917245","https://openalex.org/W3151079898","https://openalex.org/W4205752284","https://openalex.org/W7130652924","https://openalex.org/W7124183376","https://openalex.org/W4413458640"],"abstract_inverted_index":{"The":[0],"reinforcement":[1,100],"learning":[2,56,85,101],"(RL)":[3],"model":[4,24,61],"has":[5],"been":[6],"very":[7],"successful":[8],"in":[9,18,110],"behavioral":[10],"sciences,":[11],"artificial":[12],"intelligence":[13],"and":[14],"neuroscience.Despite":[15],"its":[16],"fruitfulness":[17],"many":[19,91],"simple":[20],"situations,":[21],"the":[22,54,64,77,80,84,88],"RL":[23,55],"does":[25],"not":[26,75],"always":[27],"cope":[28],"well":[29],"with":[30],"real":[31],"life":[32],"situations":[33],"involving":[34],"a":[35,43,50,107,111],"large":[36,44],"space":[37],"of":[38,46,53,59,79,83,90,97],"possible":[39,47,92],"world":[40],"states":[41],"or":[42],"set":[45],"actions.We":[48],"propose":[49],"modified":[51,99],"version":[52],"model.The":[57],"benefit":[58],"this":[60,98],"is":[62,104],"that":[63],"temporal":[65],"difference":[66],"prediction":[67],"error":[68],"can":[69],"be":[70],"used":[71],"directly":[72],"to":[73],"update":[74],"only":[76],"value":[78],"latest":[81],"action":[82],"agent,":[86],"but":[87],"values":[89],"future":[93],"actions.An":[94],"example":[95],"application":[96],"infrastructure":[102],"(MRLI)":[103],"presented":[105],"for":[106],"customer":[108],"behaviour":[109],"complex":[112],"shopping":[113],"environment.":[114]},"counts_by_year":[{"year":2020,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}