q_net_theano.py 文件源码

def chooseBestAction(self, state):
        """ Get the best action for a belief state

        Arguments
        ---------
        state : one belief state

        Returns
        -------
        The best action : int
        """        
        q_vals = self.qValues(state)

        return np.argmax(q_vals),np.max(q_vals)