Matches in SemOpenAlex for { <https://semopenalex.org/work/W3178286989> ?p ?o ?g. }
- W3178286989 endingPage "106010" @default.
- W3178286989 startingPage "106010" @default.
- W3178286989 abstract "In this work, we address a new feedforward control scheme of the normalized beta (βN) in tokamak plasmas, using the deep reinforcement learning (RL) technique. The deep RL algorithm optimizes an artificial decision-making agent that adjusts the discharge scenario to obtain the given target βN, from the state-action-reward sets explored by trials and errors of itself in the virtual tokamak environment. The virtual environment for the RL training is constructed with the LSTM network that imitates the plasma responses by external actuator controls, which is trained from 5-year KSTAR experimental data. Then, the RL agent experiences tons of discharges with different actuator controls in the LSTM simulator, and its internal parameters are optimized in the direction of maximizing the reward. We analyze a series of KSTAR experiments conducted with the RL-determined scenarios to validate the feasibility of the beta control scheme in a real device. We discuss the successes and limitations of the feedforward beta control by RL, and suggest our future works about it." @default.
- W3178286989 created "2021-07-19" @default.
- W3178286989 creator A5002041720 @default.
- W3178286989 creator A5023480923 @default.
- W3178286989 creator A5031024072 @default.
- W3178286989 creator A5048277362 @default.
- W3178286989 creator A5061926295 @default.
- W3178286989 creator A5088507688 @default.
- W3178286989 creator A5089801298 @default.
- W3178286989 date "2021-09-02" @default.
- W3178286989 modified "2023-10-16" @default.
- W3178286989 title "Feedforward beta control in the KSTAR tokamak by deep reinforcement learning" @default.
- W3178286989 cites W1968169452 @default.
- W3178286989 cites W1973604830 @default.
- W3178286989 cites W1974149462 @default.
- W3178286989 cites W2009512802 @default.
- W3178286989 cites W2014101156 @default.
- W3178286989 cites W2016422029 @default.
- W3178286989 cites W2017386005 @default.
- W3178286989 cites W2040802271 @default.
- W3178286989 cites W2042991538 @default.
- W3178286989 cites W2044744809 @default.
- W3178286989 cites W2055420683 @default.
- W3178286989 cites W2061612131 @default.
- W3178286989 cites W2064675550 @default.
- W3178286989 cites W2066816693 @default.
- W3178286989 cites W2070410930 @default.
- W3178286989 cites W2076592004 @default.
- W3178286989 cites W2079591929 @default.
- W3178286989 cites W2081965316 @default.
- W3178286989 cites W2082516490 @default.
- W3178286989 cites W2107766896 @default.
- W3178286989 cites W2109594604 @default.
- W3178286989 cites W2121529216 @default.
- W3178286989 cites W2125659415 @default.
- W3178286989 cites W2128394665 @default.
- W3178286989 cites W2130312367 @default.
- W3178286989 cites W2145339207 @default.
- W3178286989 cites W2216104499 @default.
- W3178286989 cites W2289702106 @default.
- W3178286989 cites W2467263683 @default.
- W3178286989 cites W2622651081 @default.
- W3178286989 cites W2752320568 @default.
- W3178286989 cites W2762322237 @default.
- W3178286989 cites W2766872617 @default.
- W3178286989 cites W2840417818 @default.
- W3178286989 cites W2937394206 @default.
- W3178286989 cites W2973915103 @default.
- W3178286989 cites W3004814571 @default.
- W3178286989 cites W3020131746 @default.
- W3178286989 cites W3101935416 @default.
- W3178286989 cites W3105016770 @default.
- W3178286989 cites W3194305027 @default.
- W3178286989 cites W659580137 @default.
- W3178286989 doi "https://doi.org/10.1088/1741-4326/ac121b" @default.
- W3178286989 hasPublicationYear "2021" @default.
- W3178286989 type Work @default.
- W3178286989 sameAs 3178286989 @default.
- W3178286989 citedByCount "17" @default.
- W3178286989 countsByYear W31782869892021 @default.
- W3178286989 countsByYear W31782869892022 @default.
- W3178286989 countsByYear W31782869892023 @default.
- W3178286989 crossrefType "journal-article" @default.
- W3178286989 hasAuthorship W3178286989A5002041720 @default.
- W3178286989 hasAuthorship W3178286989A5023480923 @default.
- W3178286989 hasAuthorship W3178286989A5031024072 @default.
- W3178286989 hasAuthorship W3178286989A5048277362 @default.
- W3178286989 hasAuthorship W3178286989A5061926295 @default.
- W3178286989 hasAuthorship W3178286989A5088507688 @default.
- W3178286989 hasAuthorship W3178286989A5089801298 @default.
- W3178286989 hasConcept C116515362 @default.
- W3178286989 hasConcept C121332964 @default.
- W3178286989 hasConcept C127413603 @default.
- W3178286989 hasConcept C133731056 @default.
- W3178286989 hasConcept C159985019 @default.
- W3178286989 hasConcept C185544564 @default.
- W3178286989 hasConcept C192562407 @default.
- W3178286989 hasConcept C199360897 @default.
- W3178286989 hasConcept C2776174256 @default.
- W3178286989 hasConcept C2780166548 @default.
- W3178286989 hasConcept C38858127 @default.
- W3178286989 hasConcept C41008148 @default.
- W3178286989 hasConcept C67203356 @default.
- W3178286989 hasConcept C82706917 @default.
- W3178286989 hasConceptScore W3178286989C116515362 @default.
- W3178286989 hasConceptScore W3178286989C121332964 @default.
- W3178286989 hasConceptScore W3178286989C127413603 @default.
- W3178286989 hasConceptScore W3178286989C133731056 @default.
- W3178286989 hasConceptScore W3178286989C159985019 @default.
- W3178286989 hasConceptScore W3178286989C185544564 @default.
- W3178286989 hasConceptScore W3178286989C192562407 @default.
- W3178286989 hasConceptScore W3178286989C199360897 @default.
- W3178286989 hasConceptScore W3178286989C2776174256 @default.
- W3178286989 hasConceptScore W3178286989C2780166548 @default.
- W3178286989 hasConceptScore W3178286989C38858127 @default.
- W3178286989 hasConceptScore W3178286989C41008148 @default.
- W3178286989 hasConceptScore W3178286989C67203356 @default.
- W3178286989 hasConceptScore W3178286989C82706917 @default.