Exploration Entropy for Reinforcement Learning

Figure 10

The learning control performance of RL algorithms is used by the three-switch control method. For each algorithm, the step convergence effect, the Exploration Entropy effect, the quantum system state transition path, and the control sequence learned (0 for no pulse, −1 for negative pulse, and +1 for positive pulse) are shown separately. (a) Q-learning. (b) PQL.

(a)

(b)