代码拉取完成,页面将自动刷新
from collections import deque
import random
class ReplayBuffer(object):
def __init__(self, buffer_size):
self.buffer_size = buffer_size
self.num_experiences = 0
self.buffer = deque()
def get_batch(self, batch_size):
# Randomly sample batch_size examples
return random.sample(self.buffer, batch_size)
def size(self):
return self.buffer_size
def add(self, state, action, reward, new_state, done):
experience = (state, action, reward, new_state, done)
if self.num_experiences < self.buffer_size:
self.buffer.append(experience)
self.num_experiences += 1
else:
self.buffer.popleft()
self.buffer.append(experience)
def count(self):
# if buffer is full, return buffer size
# otherwise, return experience counter
return self.num_experiences
def erase(self):
self.buffer = deque()
self.num_experiences = 0
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。