The success of reinforcement learning (RL)-based control in tokamaks, an emerging technique for controlled nuclear fusion with improved flexibility, typically requires substantial interaction with a simulator capable of accurately evolving the high-dimensional plasma state. Compared to first-principle-based simulators, whose intense computations lead to sluggish RL training, we devise an effective method to acquire a fully data-driven simulator, by mitigating the arising compounding error issue due to the underlyi…