{"id":"https://openalex.org/W4312277666","doi":"https://doi.org/10.1109/tai.2022.3225256","title":"Deep Reinforcement Learning With Reward Design for Quantum Control","display_name":"Deep Reinforcement Learning With Reward Design for Quantum Control","publication_year":2022,"publication_date":"2022-11-28","ids":{"openalex":"https://openalex.org/W4312277666","doi":"https://doi.org/10.1109/tai.2022.3225256"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2022.3225256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2022.3225256","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-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/A5067924784","display_name":"Haixu Yu","orcid":"https://orcid.org/0000-0003-2953-747X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haixu Yu","raw_affiliation_strings":["Key Laboratory of Intelligent Control and Optimization for Industrial Equipment, Ministry of Education, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Control and Optimization for Industrial Equipment, Ministry of Education, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083349103","display_name":"Xudong Zhao","orcid":"https://orcid.org/0000-0002-1864-4686"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Zhao","raw_affiliation_strings":["Key Laboratory of Intelligent Control and Optimization for Industrial Equipment, Ministry of Education, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Control and Optimization for Industrial Equipment, Ministry of Education, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067924784"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":2.7787,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91753186,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"5","issue":"3","first_page":"1087","last_page":"1101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9991000294685364,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9991000294685364,"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/T10020","display_name":"Quantum Information and Cryptography","score":0.9986000061035156,"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/T11520","display_name":"Advanced Thermodynamics and Statistical Mechanics","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8507028818130493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5365834832191467},{"id":"https://openalex.org/keywords/qubit","display_name":"Qubit","score":0.48956021666526794},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.46686863899230957},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4615829586982727},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45893144607543945},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.45612019300460815},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4386720061302185},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4283970892429352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39240461587905884},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17557895183563232},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11671623587608337},{"id":"https://openalex.org/keywords/quantum-mechanics","display_name":"Quantum mechanics","score":0.08526736497879028}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8507028818130493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5365834832191467},{"id":"https://openalex.org/C203087015","wikidata":"https://www.wikidata.org/wiki/Q378201","display_name":"Qubit","level":3,"score":0.48956021666526794},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.46686863899230957},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4615829586982727},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45893144607543945},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.45612019300460815},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4386720061302185},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4283970892429352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39240461587905884},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17557895183563232},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11671623587608337},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.08526736497879028},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2022.3225256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2022.3225256","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1492753165","display_name":null,"funder_award_id":"U21A20477","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2446255568","display_name":null,"funder_award_id":"61722302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3641551724","display_name":null,"funder_award_id":"DUT22ZD402","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1530682388","https://openalex.org/W1571271309","https://openalex.org/W1620538313","https://openalex.org/W1966963299","https://openalex.org/W1978533437","https://openalex.org/W1986160866","https://openalex.org/W2014088566","https://openalex.org/W2024771919","https://openalex.org/W2054438887","https://openalex.org/W2059836092","https://openalex.org/W2092479209","https://openalex.org/W2117302943","https://openalex.org/W2139612737","https://openalex.org/W2145339207","https://openalex.org/W2165501169","https://openalex.org/W2419175238","https://openalex.org/W2582157661","https://openalex.org/W2743614741","https://openalex.org/W2761015455","https://openalex.org/W2768956845","https://openalex.org/W2772265515","https://openalex.org/W2786295636","https://openalex.org/W2787941237","https://openalex.org/W2881153414","https://openalex.org/W2914809905","https://openalex.org/W2941137921","https://openalex.org/W2948244328","https://openalex.org/W2954329902","https://openalex.org/W2958187629","https://openalex.org/W2966477753","https://openalex.org/W2981230670","https://openalex.org/W2990961515","https://openalex.org/W3025584654","https://openalex.org/W3037776276","https://openalex.org/W3084357507","https://openalex.org/W3099024081","https://openalex.org/W3101119258","https://openalex.org/W3102180547","https://openalex.org/W3103107186","https://openalex.org/W3103145727","https://openalex.org/W3106048280","https://openalex.org/W3107552890","https://openalex.org/W3113564242","https://openalex.org/W3115010286","https://openalex.org/W3139389937","https://openalex.org/W3140011305","https://openalex.org/W3153434261","https://openalex.org/W3164005523","https://openalex.org/W3185548723","https://openalex.org/W3185930291","https://openalex.org/W3186201815","https://openalex.org/W3188946160","https://openalex.org/W3197561825","https://openalex.org/W4206943636","https://openalex.org/W4214717370","https://openalex.org/W4220756364","https://openalex.org/W4283717319","https://openalex.org/W6638088447","https://openalex.org/W6682205418","https://openalex.org/W6792358862","https://openalex.org/W6793673822"],"related_works":["https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W3125091513","https://openalex.org/W4318832338","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W1919390113","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,52,58,177],"(DRL)":[3],"has":[4],"been":[5],"recognized":[6],"as":[7],"a":[8,42,45,78,98,121],"powerful":[9],"tool":[10],"in":[11,88],"quantum":[12,23,156,162],"physics,":[13],"where":[14,56],"DRL's":[15,38,139],"reward":[16,47,117,127,146],"design":[17,37,115],"is":[18,95,106,151],"nontrivial":[19],"but":[20],"crucial":[21],"for":[22,138],"control":[24,157,164,180,197,201],"tasks.":[25],"To":[26],"address":[27],"the":[28,51,57,63,67,71,82,89,102,109,116,125,132,148,160,171,175,183,192,196],"problem":[29],"of":[30,182],"over-reliance":[31],"on":[32,153],"human":[33],"empirical":[34],"knowledge":[35],"to":[36,108,114,135,143,194,204],"rewards,":[39],"we":[40],"propose":[41],"DRL":[43],"with":[44,131,199],"novel":[46],"paradigm":[48],"designed":[49,126],"by":[50,77,119],"process":[53,59,94],"information":[54,60,65,73,105],"(DRL-LPI),":[55],"(LPI)":[61],"comprises":[62],"state":[64,72,104,163,168],"and":[66,81,92,112,165,170,179,209],"experiences.":[68],"In":[69],"DRL-LPI,":[70],"after":[74],"being":[75],"classified":[76],"fidelity":[79],"threshold,":[80],"experiences":[83,134],"are":[84,129],"first":[85],"stored":[86,103,133],"simultaneously":[87],"respective":[90],"sequences,":[91],"this":[93],"repeated":[96],"until":[97],"similar-segment":[99],"ends.":[100],"Then,":[101],"converted":[107],"real":[110],"value":[111,118],"used":[113],"applying":[120],"self-amplitude":[122],"function.":[123],"Next,":[124],"values":[128],"integrated":[130],"compose":[136],"transitions":[137],"training.":[140],"Through":[141],"comparisons":[142],"five":[144],"representative":[145],"schemes,":[147],"proposed":[149,184],"DRL-LPI":[150,190],"evaluated":[152],"two":[154],"typical":[155],"tasks,":[158],"i.e.,":[159],"spin-(1/2)":[161],"many-coupled":[166],"qubits":[167],"control,":[169],"experimental":[172],"results":[173,187],"show":[174,188],"superior":[176],"efficiency":[178],"performance":[181],"approach.":[185],"More":[186],"that":[189],"exhibits":[191],"ability":[193],"learn":[195],"strategy":[198],"few":[200],"actions":[202],"compared":[203],"stochastic":[205],"gradient":[206],"descent":[207],"(SGD)":[208],"genetic":[210],"algorithm":[211],"(GA).":[212]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}