dqn.py 文件源码

def act(self, state):
        with chainer.using_config('train', False):
            with chainer.no_backprop_mode():
                action_value = self.model(
                    self.batch_states([state], self.xp, self.phi))
                q = float(action_value.max.data)
                action = cuda.to_cpu(action_value.greedy_actions.data)[0]

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

        self.logger.debug('t:%s q:%s action_value:%s', self.t, q, action_value)
        return action