{"id":"https://openalex.org/W2076085057","doi":"https://doi.org/10.1109/foci.2007.371540","title":"Designing the Reward System: Computational and Biological Principles","display_name":"Designing the Reward System: Computational and Biological Principles","publication_year":2007,"publication_date":"2007-04-01","ids":{"openalex":"https://openalex.org/W2076085057","doi":"https://doi.org/10.1109/foci.2007.371540","mag":"2076085057"},"language":"en","primary_location":{"id":"doi:10.1109/foci.2007.371540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/foci.2007.371540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Symposium on Foundations of Computational Intelligence","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/A5004840638","display_name":"Kenji Doya","orcid":"https://orcid.org/0000-0002-2446-6820"},"institutions":[{"id":"https://openalex.org/I142637625","display_name":"Okinawa Institute of Science and Technology Graduate University","ror":"https://ror.org/02qg15b79","country_code":"JP","type":"education","lineage":["https://openalex.org/I142637625"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kenji Doya","raw_affiliation_strings":["Okinawa Institute of Science and Technology, Japan","Okinawa Institute of Science & Technology"],"affiliations":[{"raw_affiliation_string":"Okinawa Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I142637625"]},{"raw_affiliation_string":"Okinawa Institute of Science & Technology","institution_ids":["https://openalex.org/I142637625"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004840638"],"corresponding_institution_ids":["https://openalex.org/I142637625"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09628621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"645","last_page":"645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9108999967575073,"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":0.9108999967575073,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9018999934196472,"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":0.7819629907608032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7431832551956177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5688148736953735},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5416318774223328},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5267642736434937},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4726870357990265},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46227818727493286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3821389675140381}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7819629907608032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7431832551956177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5688148736953735},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5416318774223328},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5267642736434937},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4726870357990265},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46227818727493286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3821389675140381},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/foci.2007.371540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/foci.2007.371540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Symposium on Foundations of Computational Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2032610016","https://openalex.org/W2075323224","https://openalex.org/W2161563886"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W4388311650","https://openalex.org/W5922282","https://openalex.org/W1974056099","https://openalex.org/W4245343541","https://openalex.org/W2386077341","https://openalex.org/W563589758","https://openalex.org/W62490179","https://openalex.org/W2954004777","https://openalex.org/W2951102138"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"In":[4,32],"the":[5,45,57,73],"standard":[6],"framework":[7],"of":[8,47,69,85,90,108,136,142],"optimal":[9],"control":[10,35,119],"and":[11,23,37,64,117,120,128,139],"reinforcement":[12],"learning,":[13],"a":[14,21,51],"\"cost\"":[15],"or":[16],"\"reward\"":[17],"function":[18,54],"is":[19,27,72,93,99],"given":[20],"priori,":[22],"an":[24,60,94,100],"intelligent":[25,78],"agent":[26,58],"supposed":[28],"to":[29,49,55,80,104,114,131],"optimize":[30],"it.":[31],"real":[33],"life,":[34],"engineers":[36],"machine":[38],"learning":[39],"researchers":[40],"are":[41,123],"often":[42],"faced":[43],"with":[44],"problem":[46],"how":[48],"design":[50],"good":[52],"objective":[53],"let":[56],"attain":[59],"intended":[61],"goal":[62],"efficiently":[63],"reliably.":[65],"Such":[66],"meta-level":[67],"tuning":[68],"adaptive":[70,91],"processes":[71],"major":[74],"challenge":[75],"in":[76],"bringing":[77],"agents":[79,92],"real-world":[81],"applications.":[82],"While":[83],"development":[84],"theoretical":[86],"frameworks":[87],"for":[88],"'meta-learning'":[89],"urgent":[95],"engineering":[96],"problem,":[97],"it":[98],"important":[101],"biological":[102,140],"question":[103],"ask":[105],"what":[106],"kind":[107],"meta-learning":[109,143],"mechanisms":[110],"our":[111],"brain":[112],"implements":[113],"enable":[115],"robust":[116],"flexible":[118],"learning.":[121],"We":[122],"putting":[124],"together":[125],"computational,":[126],"neurobiological,":[127],"robotic":[129],"approaches":[130],"attack":[132],"these":[133],"dual":[134],"problems":[135],"computational":[137],"theory":[138],"implementation":[141]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}