wrappers.py 文件源码

def __init__(self, env, cmdl):
        super(VisdomMonitor, self).__init__(env)

        self.freq = cmdl.report_freq  # in steps
        self.cmdl = cmdl

        if self.cmdl.display_plots:
            from visdom import Visdom
            self.vis = Visdom()
            self.plot = self.vis.line(
                Y=np.array([0]), X=np.array([0]),
                opts=dict(
                    title=cmdl.label,
                    caption="Episodic reward per 1200 steps.")
            )

        self.step_cnt = 0
        self.ep_cnt = -1
        self.ep_rw = []
        self.last_reported_ep = 0