bd2ab5ff212c46435cdebafc02f4801d65f3df33,slm_lab/agent/__init__.py,Body,calc_df_row,#Body#Any#,127

Before Change

            "opt_step": self.env.clock.get("opt_step"),
            "frame": frame,
            "fps": fps,
            "total_reward": np.nanmean(env.total_reward),  // guard for vec env
            "total_reward_ma": np.nan,  // update outside
            "loss": self.loss,
            "lr": self.get_mean_lr(),

After Change

        wall_t = env.clock.get_elapsed_wall_t()
        fps = 0 if wall_t == 0 else frame / wall_t
        with np.errstate(all="ignore"):
            total_reward = np.nanmean(env.total_reward)  // guard for vec env

        // update debugging variables
        if net_util.to_check_train_step():

Instances