{"id":"https://openalex.org/W2784070433","doi":"https://doi.org/10.1109/cdc.2017.8264148","title":"Feature extraction in Q-learning using neural networks","display_name":"Feature extraction in Q-learning using neural networks","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2784070433","doi":"https://doi.org/10.1109/cdc.2017.8264148","mag":"2784070433"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2017.8264148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2017.8264148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 56th Annual Conference on Decision and Control (CDC)","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/A5054049845","display_name":"Henghui Zhu","orcid":"https://orcid.org/0000-0002-4534-6975"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Henghui Zhu","raw_affiliation_strings":["Center for Information and Systems Eng., Boston University"],"affiliations":[{"raw_affiliation_string":"Center for Information and Systems Eng., Boston University","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075696701","display_name":"Ioannis Ch. Paschalidis","orcid":"https://orcid.org/0000-0002-3343-2913"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioannis Ch. Paschalidis","raw_affiliation_strings":["Department of Electrical and Computer Eng., Boston University, Boston, MA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Eng., Boston University, Boston, MA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088108309","display_name":"Michael E. Hasselmo","orcid":"https://orcid.org/0000-0002-9925-6377"},"institutions":[{"id":"https://openalex.org/I4210155419","display_name":"Center for Systems Biology","ror":"https://ror.org/05r3dyn47","country_code":"US","type":"facility","lineage":["https://openalex.org/I136199984","https://openalex.org/I4210087915","https://openalex.org/I4210155419","https://openalex.org/I48633490"]},{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael E. Hasselmo","raw_affiliation_strings":["Center for Systems Neuroscience, Boston University"],"affiliations":[{"raw_affiliation_string":"Center for Systems Neuroscience, Boston University","institution_ids":["https://openalex.org/I4210155419","https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054049845"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":null,"apc_paid":null,"fwci":0.7801,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80404504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3330","last_page":"3335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"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/T10320","display_name":"Neural Networks and Applications","score":0.9958999752998352,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.7485067248344421},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.730464518070221},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7038862705230713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6972947716712952},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5665823221206665},{"id":"https://openalex.org/keywords/types-of-artificial-neural-networks","display_name":"Types of artificial neural networks","score":0.5387576222419739},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5307295918464661},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5201892852783203},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5006699562072754},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47964125871658325},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44904765486717224},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44410374760627747},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.43938320875167847},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4113743305206299},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3628479540348053},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13444185256958008},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05612626671791077}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7485067248344421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.730464518070221},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7038862705230713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6972947716712952},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5665823221206665},{"id":"https://openalex.org/C177973122","wikidata":"https://www.wikidata.org/wiki/Q7860946","display_name":"Types of artificial neural networks","level":4,"score":0.5387576222419739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5307295918464661},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5201892852783203},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5006699562072754},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47964125871658325},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44904765486717224},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44410374760627747},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.43938320875167847},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4113743305206299},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3628479540348053},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13444185256958008},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05612626671791077},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2017.8264148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2017.8264148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 56th Annual Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1964782533","https://openalex.org/W2009303086","https://openalex.org/W2041367235","https://openalex.org/W2048425408","https://openalex.org/W2098432798","https://openalex.org/W2106471678","https://openalex.org/W2139418546","https://openalex.org/W2145339207","https://openalex.org/W2147750403","https://openalex.org/W2519553506","https://openalex.org/W2557283755","https://openalex.org/W2585198072","https://openalex.org/W2620827312","https://openalex.org/W2919115771","https://openalex.org/W2963616477","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W4233696721","https://openalex.org/W4253020087","https://openalex.org/W4307347247","https://openalex.org/W6637242042","https://openalex.org/W6692846177","https://openalex.org/W6730267373"],"related_works":["https://openalex.org/W2315999538","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532","https://openalex.org/W1584270863","https://openalex.org/W2149978162","https://openalex.org/W2083677758","https://openalex.org/W2950022897","https://openalex.org/W1973323485","https://openalex.org/W2373874059"],"abstract_inverted_index":{"Integrating":[0],"deep":[1],"neural":[2,18,61,83,112,118],"networks":[3,19,119],"with":[4,26,59,98,111],"reinforcement":[5],"learning":[6],"has":[7],"exhibited":[8],"excellent":[9],"performance":[10,104],"in":[11,50,94,126],"the":[12,15,67,79,127],"literature,":[13],"highlighting":[14],"ability":[16],"of":[17,81,129],"to":[20,85,106],"extract":[21,86],"features.":[22],"This":[23],"paper":[24],"begins":[25],"a":[27,34,45,60,82,95,99],"simple":[28],"Markov":[29],"decision":[30],"process":[31],"inspired":[32],"from":[33],"cognitive":[35],"task.":[36,52],"We":[37],"show":[38,55],"that":[39,56,77,107,117],"Q-learning,":[40],"and":[41],"approximate":[42],"Q-learning":[43,57,96,110],"using":[44,109],"linear":[46,100],"function":[47,63,101],"approximation":[48],"fail":[49],"this":[51,72],"Instead,":[53],"we":[54,74],"combined":[58],"network-based":[62],"approximator":[64],"can":[65,90,120],"learn":[66],"optimal":[68],"policy.":[69],"Motivated":[70],"by":[71],"finding,":[73],"outline":[75],"procedures":[76],"allow":[78],"use":[80],"network":[84],"appropriate":[87],"features,":[88],"which":[89],"then":[91],"be":[92,121],"used":[93,122],"framework":[97],"approximation,":[102],"obtaining":[103],"similar":[105],"observed":[108],"networks.":[113],"Our":[114],"work":[115],"suggests":[116],"as":[123],"feature":[124],"extractors":[125],"context":[128],"Q-learning.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}