reinforce.py 文件源码

def act(self, obs):
        with chainer.no_backprop_mode():
            batch_obs = self.batch_states([obs], self.xp, self.phi)
            action_distrib = self.model(batch_obs)
            if self.act_deterministically:
                return chainer.cuda.to_cpu(
                    action_distrib.most_probable.data)[0]
            else:
                return chainer.cuda.to_cpu(action_distrib.sample().data)[0]