def RNN_forward_prop(X, Y, a0, parameters, vocab_size):

    x = {}
    a = {}
    y_hat = {}
    a[-1] = np.copy(a0)
    loss= 0

    # Iterate for the T timesteps
    for t in range(len(X)):

        # One-hot representation of the t-th character
        x[t] = np.zeros((vocab_size, 1))
        if X[t] != None:
            x[t][X[t]] = 1

        # Run one timestep of forward prop
        a[t], y_hat[t] = RNN_forward_prop_step(parameters, a[t-1], x[t])

        # Update loss function
        loss -= np.log(y_hat[t][Y[t],0])

    cache = (y_hat, a, x)

    return loss, cache