pgt.py 文件源码

def act(self, state):

        with chainer.using_config('train', False):
            s = self.batch_states([state], self.xp, self.phi)
            if self.act_deterministically:
                action = self.policy(s).most_probable
            else:
                action = self.policy(s).sample()
            # Q is not needed here, but log it just for information
            q = self.q_function(s, action)

        # Update stats
        self.average_q *= self.average_q_decay
        self.average_q += (1 - self.average_q_decay) * float(q.data)

        self.logger.debug('t:%s a:%s q:%s',
                          self.t, action.data[0], q.data)
        return cuda.to_cpu(action.data[0])