Development of an operation trajectory design algorithm for control of multiple 0D parameters using deep reinforcement learning in KSTAR

Jaemin Seo(Seoul National University), Y.H. Lee(Korea Telecom (South Korea)), M.S. Park(Seoul National University), B. Kim(Seoul National University), Yong-Su Na(Seoul National University), Seong‐Jik Park(Hankyong National University), Chanyoung Lee(Korea Institute of Fusion Energy)
Nuclear Fusion
June 17, 2022
10.1088/1741-4326/ac79be
Cited by 31

Related Papers

A sustained high-temperature fusion plasma regime facilitated by fast ions
|Nature|2022|123
The ‘hybrid’ scenario in JET: towards its validation for ITER
|Nuclear Fusion|2005|111
Feedforward beta control in the KSTAR tokamak by deep reinforcement learning
|Nuclear Fusion|2021|63
On hybrid scenarios in KSTAR
|Nuclear Fusion|2020|49
Highest fusion performance without harmful edge energy bursts in tokamak
|Nature Communications|2024|35