QLearnerAgentClass.py 文件源码

def get_action_distr(self, state, beta=0.2):
        '''
        Args:
            state (State)
            beta (float): Softmax temperature parameter.

        Returns:
            (list of floats): The i-th float corresponds to the probability
            mass associated with the i-th action (indexing into self.actions)
        '''
        all_q_vals = []
        for i in xrange(len(self.actions)):
            action = self.actions[i]
            all_q_vals.append(self.get_q_value(state, action))

        # Softmax distribution.
        total = sum([numpy.exp(beta * qv) for qv in all_q_vals])
        softmax = [numpy.exp(beta * qv) / total for qv in all_q_vals]

        return softmax