def normalize(self, new_state):
# Update
self.count += 1
self.sum += new_state
self.sum_sqr += new_state**2
if self.count % self.update_freq == 0 and False:
self._update()
# Normalize
new_state = new_state - self.mean
new_state = new_state / self.std
new_state = np.clip(new_state, -self.clip, self.clip)
return new_state
评论列表
文章目录