06279f054fcfa03517b1bd51ef156a9182af146f,examples/grid_world.py,,,#,59

Before Change

            r = np.array([o[0] for o in out])
            max_Qs = np.array([o[1] for o in out])

            np.save("r" + names[a] + names[e] + ".npy",
                    np.convolve(np.mean(r, 0), np.ones(100) / 100., "valid"))
            np.save("max_Q" + names[a] + names[e] + ".npy", np.mean(max_Qs, 0))

After Change

            from matplotlib import pyplot as plt
            plt.plot(np.convolve(
                np.mean(r, axis=0), np.ones(100) / 100., "valid"))
            plt.figure()
            plt.plot(np.mean(max_Qs, axis=0))
            plt.show()
            exit()

Instances