This repo trains a DDPG agent (MATLAB Reinforcement Learning Toolbox) to tune a FOPID controller inside a Simulink model (RL_Model.slx) for a self-balancing robot (inverted-pendulum-like). The agent ...
Abstract: We report a newly developed room-temperature (RT) shimming method for high-temperature superconducting (HTS) magnets employing a deep Q-network (DQN), a type of reinforcement learning theory ...