agent_rl.py 文件源码

def get_epsilon_k(self):
        '''
        Get $\epsilon_k$ according to the exploration schedule
        '''
        trial = self.env.count_trials - 2  # ?
        if self.decayfun == 'tpower':
            # e = a^t, where 0 < z < 1
            # self.f_epsilon = math.pow(0.9675, trial)  # for 100 trials
            self.f_epsilon = math.pow(0.9333, trial)  # for 50 trials

        elif self.decayfun == 'trig':
            # e = cos(at), where 0 < z < 1
            # self.f_epsilon = math.cos(0.0168 * trial)  # for 100 trials
            self.f_epsilon = math.cos(0.03457 * trial)  # for 50 trials
        else:
            # self.f_epsilon = max(0., 1. - (1./45. * trial))  # for 50 trials
            self.f_epsilon = max(0., 1. - (1./95. * trial))  # for 100 trials
        return self.f_epsilon