{"id":"https://openalex.org/W7123351297","doi":"https://doi.org/10.1109/cdc57313.2025.11312651","title":"Control of a Bi-Stable Genetic System via Parallelized Reinforcement Learning","display_name":"Control of a Bi-Stable Genetic System via Parallelized Reinforcement Learning","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123351297","doi":"https://doi.org/10.1109/cdc57313.2025.11312651"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th 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/A5109897735","display_name":"R D Henry","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Robin Henry","raw_affiliation_strings":["University of Oxford,Department of Engineering Science,Oxford,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford,Department of Engineering Science,Oxford,United Kingdom","institution_ids":["https://openalex.org/I4210146410","https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049621342","display_name":"Jean\u2010Baptiste Lugagne","orcid":"https://orcid.org/0000-0002-8374-6590"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jean-Baptiste Lugagne","raw_affiliation_strings":["University of Oxford,Department of Engineering Science,Oxford,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford,Department of Engineering Science,Oxford,United Kingdom","institution_ids":["https://openalex.org/I4210146410","https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109897735"],"corresponding_institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66598037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2898","last_page":"2904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9550999999046326,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9550999999046326,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.01360000018030405,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.004000000189989805,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7847999930381775},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5245000123977661},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4948999881744385},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.41040000319480896},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4066999852657318},{"id":"https://openalex.org/keywords/feedback-control","display_name":"Feedback control","score":0.3912999927997589},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.36410000920295715},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.36320000886917114}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7847999930381775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034000158309937},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5245000123977661},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41990000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41929998993873596},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C97292510","wikidata":"https://www.wikidata.org/wiki/Q2304620","display_name":"Bistability","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.27709999680519104},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2676999866962433},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C167123822","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automatic control","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Achieving":[0],"real-time":[1],"control":[2,67,105,123,139,150,187],"of":[3,15,24,41,65,93,112,188],"genetic":[4,56],"systems":[5,26],"is":[6],"critical":[7],"for":[8,78,125,165,184],"improving":[9],"the":[10,21,63,88,100,110,155],"reliability,":[11],"efficiency,":[12],"and":[13,18,53,69,91,148],"reproducibility":[14],"biological":[16,72,191],"research":[17],"engineering.":[19],"Yet":[20],"intrinsic":[22],"stochasticity":[23],"these":[25],"makes":[27],"this":[28,140],"goal":[29],"difficult.":[30],"Prior":[31],"efforts":[32],"have":[33],"faced":[34],"three":[35],"recurring":[36],"challenges:":[37],"(a)":[38],"predictive":[39],"models":[40],"gene":[42,129],"expression":[43],"dynamics":[44,52],"are":[45],"often":[46],"inaccurate":[47],"or":[48],"unavailable,":[49],"(b)":[50],"nonlinear":[51],"feedback":[54],"in":[55,154,177],"circuits":[57],"frequently":[58],"lead":[59],"to":[60,102,121,162],"multi-stability,":[61],"limiting":[62],"effectiveness":[64],"deterministic":[66],"strategies,":[68],"(c)":[70],"slow":[71],"response":[73],"times":[74],"make":[75],"data":[76],"collection":[77],"learning-based":[79],"methods":[80,151],"prohibitively":[81],"time-consuming.":[82],"Recent":[83],"experimental":[84,166],"advances":[85,176],"now":[86],"allow":[87],"parallel":[89],"observation":[90],"manipulation":[92],"over":[94],"a":[95,116,126,181],"million":[96],"individual":[97],"cells,":[98],"opening":[99],"door":[101],"model-free,":[103],"data-driven":[104],"strategies.":[106],"Here":[107],"we":[108],"investigate":[109],"use":[111],"Parallelized":[113],"Q-Networks":[114],"(PQN),":[115],"recently-developed":[117],"reinforcement":[118,178],"learning":[119,179],"algorithm,":[120],"learn":[122],"policies":[124],"simulated":[127],"bistable":[128],"regulatory":[130],"network.":[131],"We":[132],"show":[133],"that":[134,171],"PQN":[135],"can":[136],"not":[137],"only":[138],"self-activating":[141],"system":[142],"more":[143],"accurately":[144],"than":[145],"other":[146],"model-free":[147,186],"model-based":[149],"previously":[152],"used":[153],"field,":[156],"but":[157],"also":[158],"converges":[159],"efficiently":[160],"enough":[161],"be":[163],"practical":[164],"application.":[167],"Our":[168],"results":[169],"suggest":[170],"parallelized":[172],"experiments":[173],"coupled":[174],"with":[175],"provide":[180],"viable":[182],"path":[183],"real-time,":[185],"complex,":[189],"multi-stable":[190],"systems.":[192]},"counts_by_year":[],"updated_date":"2026-01-14T00:46:21.520733","created_date":"2026-01-14T00:00:00"}