-
Notifications
You must be signed in to change notification settings - Fork 32
/
run.py
176 lines (150 loc) · 8.25 KB
/
run.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
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
import numpy as np
import random
import gym
import pybulletgym # to run e.g. HalfCheetahPyBullet-v0
import pybullet_envs # to run e.g. HalfCheetahBullet-v0 different reward function bullet-v0 starts ~ -1500. pybullet-v0 starts at 0
from collections import deque
import torch
import time
from torch.utils.tensorboard import SummaryWriter
import argparse
from files import MultiPro
from files.Agent import Agent
import json
def timer(start,end):
""" Helper to print training time """
hours, rem = divmod(end-start, 3600)
minutes, seconds = divmod(rem, 60)
print("\nTraining Time: {:0>2}:{:0>2}:{:05.2f}".format(int(hours),int(minutes),seconds))
def evaluate(frame, eval_runs=5, capture=False, render=False):
"""
Makes an evaluation run with the current epsilon
"""
reward_batch = []
for i in range(eval_runs):
if render:
print(render)
eval_env.render(mode="human")
state = eval_env.reset()
rewards = 0
while True:
action = agent.act(np.expand_dims(state, axis=0), eval=True)