additive_ou.py 文件源码

def select_action(self, t, greedy_action_func, action_value=None):
        a = greedy_action_func()
        if self.ou_state is None:
            if self.start_with_mu:
                self.ou_state = np.full(a.shape, self.mu, dtype=np.float32)
            else:
                sigma_stable = (self.sigma /
                                np.sqrt(2 * self.theta - self.theta ** 2))
                self.ou_state = np.random.normal(
                    size=a.shape,
                    loc=self.mu, scale=sigma_stable).astype(np.float32)
        else:
            self.evolve()
        noise = self.ou_state
        self.logger.debug('t:%s noise:%s', t, noise)
        return a + noise