{"id":"https://openalex.org/W4391306936","doi":"https://doi.org/10.1109/smc53992.2023.10393949","title":"Guided Reward Design in Continuous Reinforcement Learning for Quantum Control","display_name":"Guided Reward Design in Continuous Reinforcement Learning for Quantum Control","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4391306936","doi":"https://doi.org/10.1109/smc53992.2023.10393949"},"language":"en","primary_location":{"id":"doi:10.1109/smc53992.2023.10393949","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smc53992.2023.10393949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5063402471","display_name":"Shumin Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shumin Zhou","raw_affiliation_strings":["University of Science and Technology of China,Department of Automation,Hefei,China,230027"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Department of Automation,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091591096","display_name":"Hailan Ma","orcid":"https://orcid.org/0000-0002-5039-9916"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hailan Ma","raw_affiliation_strings":["School of Engineering and Information Technology, University of New South Wales,Canberra,ACT,Australia,2600"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales,Canberra,ACT,Australia,2600","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059245882","display_name":"Sen Kuang","orcid":"https://orcid.org/0000-0002-4847-565X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Kuang","raw_affiliation_strings":["University of Science and Technology of China,Department of Automation,Hefei,China,230027"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Department of Automation,Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000582423","display_name":"Daoyi Dong","orcid":"https://orcid.org/0000-0002-7425-3559"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Daoyi Dong","raw_affiliation_strings":["School of Engineering and Information Technology, University of New South Wales,Canberra,ACT,Australia,2600","School of Engineering, Australian National University, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales,Canberra,ACT,Australia,2600","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Engineering, Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063402471"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19689686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"114","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10020","display_name":"Quantum Information and Cryptography","score":0.996999979019165,"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/T10020","display_name":"Quantum Information and Cryptography","score":0.996999979019165,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9927999973297119,"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":0.9925000071525574,"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":0.9376732110977173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6610066890716553},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5685449242591858},{"id":"https://openalex.org/keywords/qubit","display_name":"Qubit","score":0.49265676736831665},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4788260757923126},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4695858359336853},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46685081720352173},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.460814893245697},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.4318331480026245},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42193278670310974},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.411307156085968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34694936871528625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14643040299415588}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9376732110977173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6610066890716553},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5685449242591858},{"id":"https://openalex.org/C203087015","wikidata":"https://www.wikidata.org/wiki/Q378201","display_name":"Qubit","level":3,"score":0.49265676736831665},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4788260757923126},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4695858359336853},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46685081720352173},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.460814893245697},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.4318331480026245},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42193278670310974},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.411307156085968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34694936871528625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14643040299415588},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53992.2023.10393949","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smc53992.2023.10393949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":47,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W1807047624","https://openalex.org/W1978533437","https://openalex.org/W1997461667","https://openalex.org/W2057368709","https://openalex.org/W2059836092","https://openalex.org/W2108658419","https://openalex.org/W2117302943","https://openalex.org/W2121863487","https://openalex.org/W2525939318","https://openalex.org/W2761015455","https://openalex.org/W2797527950","https://openalex.org/W2914809905","https://openalex.org/W2940200844","https://openalex.org/W2941137921","https://openalex.org/W2958187629","https://openalex.org/W2963095800","https://openalex.org/W2963099939","https://openalex.org/W2969428710","https://openalex.org/W2973229164","https://openalex.org/W3083377600","https://openalex.org/W3101119258","https://openalex.org/W3103145727","https://openalex.org/W3111615419","https://openalex.org/W3115010286","https://openalex.org/W3195335649","https://openalex.org/W4206258457","https://openalex.org/W4214946518","https://openalex.org/W4221159779","https://openalex.org/W4283727457","https://openalex.org/W4286001073","https://openalex.org/W4289684174","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W4300799055","https://openalex.org/W4317941448","https://openalex.org/W4319782908","https://openalex.org/W4360898630","https://openalex.org/W4394661925","https://openalex.org/W6635508374","https://openalex.org/W6638088447","https://openalex.org/W6638103391","https://openalex.org/W6738796088","https://openalex.org/W6740801417","https://openalex.org/W6750629867","https://openalex.org/W6757184387","https://openalex.org/W6773378895"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W2250140200","https://openalex.org/W3121791438"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,23,53,83,96],"has":[2],"been":[3],"intensively":[4],"applied":[5],"to":[6,13,27,43,80],"tackle":[7],"complex":[8],"quantum":[9,69],"control":[10,58,67],"problems":[11],"owing":[12],"its":[14],"adaptability":[15],"in":[16,38,60],"dynamic":[17],"environments.":[18],"However,":[19],"commonly":[20],"used":[21],"reinforcement":[22,52,95],"algorithms":[24],"are":[25],"restricted":[26],"selecting":[28],"actions":[29],"from":[30],"a":[31,61,72,99],"discrete":[32],"action":[33,63],"space,":[34,64],"which":[35],"may":[36],"result":[37],"inaccurate":[39],"control.":[40],"In":[41],"order":[42],"surpass":[44],"this":[45],"constraint,":[46],"we":[47],"propose":[48],"an":[49],"improved":[50],"continuous":[51,62,94],"algorithm":[54,97],"that":[55,91],"can":[56,103],"generate":[57],"policies":[59],"enabling":[65],"precise":[66],"of":[68],"systems.":[70,111],"Moreover,":[71],"guided":[73,100],"reward":[74,101],"function":[75,102],"design":[76],"method":[77],"is":[78],"proposed":[79,93],"guide":[81],"the":[82,92],"process":[84],"toward":[85],"higher":[86],"fidelity.":[87],"Numerical":[88],"results":[89],"demonstrate":[90],"with":[98],"capably":[104],"prepare":[105],"states":[106],"on":[107],"one-qubit":[108],"and":[109],"two-qubit":[110]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
