utils.py 文件源码

def discount(rewards, gamma, timestamps):
    dt = np.diff(timestamps.squeeze())
    x = rewards.squeeze()
    g = np.power(gamma, dt)
    y = np.zeros_like(x)
    for n in range(len(y)):
        y[n] = x[n] + np.sum(x[n + 1:] * np.cumprod(g[n:]))
    return y