Learning from discrete-time rewards. (A, B) Rewards associated with the output y(t) and the action u_k(t) at the kth iteration step. The data here represent the rewards at the 1st and 8th iteration steps, which correspond to the learning results for the first and final trials. (C) Discrete-time rewards for the different iteration steps. It suggests that as the iteration steps go larger, the value of the discrete-time reward decreases. (D) The convergence of learned control policy. The convergence error decreases as the iteration step turns large. This ensures to increase in accuracy by simply setting the iteration step large. The ratio between the gain matrices ${\overline{K}}^k$ and ${\overline{P}}^k$ reveals the different learning capabilities in approximating the gain matrices from data.