39 lines
1.2 KiB
Python
39 lines
1.2 KiB
Python
#!/usr/bin/env python
|
|
# coding=utf-8
|
|
'''
|
|
@Author: John
|
|
@Email: johnjim0816@gmail.com
|
|
@Date: 2020-06-11 20:58:59
|
|
@LastEditor: John
|
|
@LastEditTime: 2020-06-11 20:59:20
|
|
@Discription:
|
|
@Environment: python 3.7.7
|
|
'''
|
|
import numpy as np
|
|
|
|
class OUNoise(object):
|
|
def __init__(self, action_space, mu=0.0, theta=0.15, max_sigma=0.3, min_sigma=0.3, decay_period=100000):
|
|
self.mu = mu
|
|
self.theta = theta
|
|
self.sigma = max_sigma
|
|
self.max_sigma = max_sigma
|
|
self.min_sigma = min_sigma
|
|
self.decay_period = decay_period
|
|
self.n_actions = action_space.shape[0]
|
|
self.low = action_space.low
|
|
self.high = action_space.high
|
|
self.reset()
|
|
|
|
def reset(self):
|
|
self.obs = np.ones(self.n_actions) * self.mu
|
|
|
|
def evolve_obs(self):
|
|
x = self.obs
|
|
dx = self.theta * (self.mu - x) + self.sigma * np.random.randn(self.n_actions)
|
|
self.obs = x + dx
|
|
return self.obs
|
|
|
|
def get_action(self, action, t=0):
|
|
ou_obs = self.evolve_obs()
|
|
self.sigma = self.max_sigma - (self.max_sigma - self.min_sigma) * min(1.0, t / self.decay_period)
|
|
return np.clip(action + ou_obs, self.low, self.high) |