Result: Gym-TORAX: Open-source software for integrating RL with plasma control simulators
Further Information
This paper presents Gym-TORAX, a Python package enabling the implementationof Reinforcement Learning (RL) environments for simulating plasma dynamics andcontrol in tokamaks. Users define succinctly a set of control actions andobservations, and a control objective from which Gym-TORAX creates a Gymnasiumenvironment that wraps TORAX for simulating the plasma dynamics. The objectiveis formulated through rewards depending on the simulated state of the plasmaand control action to optimize specific characteristics of the plasma, such asperformance and stability. The resulting environment instance is thencompatible with a wide range of RL algorithms and libraries and will facilitateRL research in plasma control. In its current version, one environment isreadily available, based on a ramp-up scenario of the InternationalThermonuclear Experimental Reactor (ITER).