-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathreplay_buffer.py
71 lines (51 loc) · 2.31 KB
/
replay_buffer.py
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
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
#Credit to mynkpl1998
import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
import random
from collections import namedtuple, deque
import matplotlib.pyplot as plt
import gym
#device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
class ReplayBuffer:
def __init__(self, action_size, buffer_size, batch_size, device='cpu', seed=0):
self.action_size = action_size
self.memory = deque(maxlen=buffer_size)
self.batch_size = batch_size
self.experience = namedtuple('Experience',
field_names=['state', 'action', 'reward', 'next_state', 'done'])
self.seed = random.seed(seed)
self.device = device
def add(self, state, action, reward, next_state, done):
e = self.experience(state, action, reward, next_state, done)
self.memory.append(e)
def sample(self):
experiences = random.sample(self.memory, k=self.batch_size)
states = torch.from_numpy(np.vstack([e.state for e in experiences if e is not None])).float().to(self.device)
actions = torch.from_numpy(np.vstack([e.action for e in experiences if e is not None])).long().to(self.device)
rewards = torch.from_numpy(np.vstack([e.reward for e in experiences if e is not None])).float().to(self.device)
next_states = torch.from_numpy(np.vstack([e.next_state for e in experiences if e is not None])).float().to(self.device)
dones = torch.from_numpy(np.vstack([e.done for e in experiences if e is not None]).astype(np.uint8)).float().to(self.device)
return (states, actions, rewards, next_states, dones)
def __len__(self):
return len(self.memory)
class ReplayBuffer_LSTM:
def __init__(self, action_size, buffer_size, batch_size=64, time_step = 8, seed=42):
self.action_size = action_size
self.memory = deque(maxlen=buffer_size)
self.batch_size = batch_size
self.experience = namedtuple('Experience',
field_names=['state', 'action', 'reward', 'next_state', 'done'])
self.seed = random.seed(seed)
def add_episode(self, episode):
self.memory.append(episode)
def get_batch(self, batch_size, time_step):
sampled_episodes = random.sample(self.memory, batch_size)
batch = []
for episode in sampled_episodes:
point = np.random.randint(0, len(episode) + 1 - time_step)
batch.append(episode[point: point+time_step])
return batch
def __len__(self):
return len(self.memory)