a3c.py 文件源码

def act(self, obs):
        # Use the process-local model for acting
        with chainer.no_backprop_mode():
            statevar = self.batch_states([obs], np, self.phi)
            pout, _ = self.model.pi_and_v(statevar)
            if self.act_deterministically:
                return pout.most_probable.data[0]
            else:
                return pout.sample().data[0]