acer.py 文件源码

def update_on_policy(self, statevar):
        assert self.t_start < self.t

        if not self.disable_online_update:
            if statevar is None:
                R = 0
            else:
                with chainer.no_backprop_mode():
                    with state_kept(self.model):
                        action_distrib, action_value, v = self.model(statevar)
                R = float(v.data)
            self.update(
                t_start=self.t_start, t_stop=self.t, R=R,
                states=self.past_states,
                actions=self.past_actions,
                rewards=self.past_rewards,
                values=self.past_values,
                action_values=self.past_action_values,
                action_distribs=self.past_action_distrib,
                action_distribs_mu=None,
                avg_action_distribs=self.past_avg_action_distrib)

        self.init_history_data_for_online_update()