visualize.py 文件源码

def smooth_reward_curve(x, y):
    # Halfwidth of our smoothing convolution
    halfwidth = min(31, int(np.ceil(len(x) / 30)))
    k = halfwidth
    xsmoo = x[k:-k]
    ysmoo = np.convolve(y, np.ones(2 * k + 1), mode='valid') / \
        np.convolve(np.ones_like(y), np.ones(2 * k + 1), mode='valid')
    downsample = max(int(np.floor(len(xsmoo) / 1e3)), 1)
    return xsmoo[::downsample], ysmoo[::downsample]