Spaces:
Sleeping
Sleeping
File size: 1,367 Bytes
75c7554 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 | import numpy as np
import torch
class ReplayBuffer:
def __init__(self, state_dim, action_dim, max_size=int(1e5)):
self.max_size = max_size
self.ptr = 0
self.size = 0
self.state = np.zeros((max_size, state_dim))
self.action = np.zeros((max_size, action_dim))
self.next_state = np.zeros((max_size, state_dim))
self.reward = np.zeros((max_size, 1))
self.not_done = np.zeros((max_size, 1))
self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
def add(self, state, action, next_state, reward, done):
self.state[self.ptr] = state
self.action[self.ptr] = action
self.next_state[self.ptr] = next_state
self.reward[self.ptr] = reward
self.not_done[self.ptr] = 1. - done
self.ptr = (self.ptr + 1) % self.max_size
self.size = min(self.size + 1, self.max_size)
def sample(self, batch_size):
ind = np.random.randint(0, self.size, size=batch_size)
return (
torch.FloatTensor(self.state[ind]).to(self.device),
torch.FloatTensor(self.action[ind]).to(self.device),
torch.FloatTensor(self.next_state[ind]).to(self.device),
torch.FloatTensor(self.reward[ind]).to(self.device),
torch.FloatTensor(self.not_done[ind]).to(self.device)
)
|