forked from sfujim/TD3
-
Notifications
You must be signed in to change notification settings - Fork 0
/
utils.py
67 lines (50 loc) · 2.02 KB
/
utils.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
import random
import numpy as np
# Expects tuples of (state, next_state, action, reward, done)
import torch
# Code based on:
# https://github.com/openai/baselines/blob/master/baselines/deepq/replay_buffer.py
class ReplayBuffer(object):
def __init__(self, max_size=1e6):
self.storage = []
self.max_size = max_size
self.ptr = 0
def add(self, data):
if len(self.storage) == self.max_size:
self.storage[int(self.ptr)] = data
self.ptr = (self.ptr + 1) % self.max_size
else:
self.storage.append(data)
def sample(self, batch_size):
ind = np.random.randint(0, len(self.storage), size=batch_size)
x, y, u, r, d = [], [], [], [], []
for i in ind:
X, Y, U, R, D = self.storage[i]
x.append(np.array(X, copy=False))
y.append(np.array(Y, copy=False))
u.append(np.array(U, copy=False))
r.append(np.array(R, copy=False))
d.append(np.array(D, copy=False))
return np.array(x), np.array(y), np.array(u), np.array(r).reshape(-1, 1), np.array(d).reshape(-1, 1)
def set_global_seeds(seed):
torch.manual_seed(seed)
if torch.cuda.is_available():
torch.cuda.manual_seed_all(seed)
np.random.seed(seed)
random.seed(seed)
def evaluate_policy(policy, env, eval_episodes=100):
#TODO: this function can be substantially speed up
#This function currently consumes ~30-50% of compute time
avg_reward = 0.
for _ in range(eval_episodes):
obs = env.reset()
done = False
while not done:
action = policy.select_action(np.array(obs))
obs, reward, done, _ = env.step(action)
avg_reward += reward
avg_reward /= eval_episodes
print("---------------------------------------")
print("Evaluation over %d episodes: %f" % (eval_episodes, avg_reward))
print("---------------------------------------")
return avg_reward