-
Notifications
You must be signed in to change notification settings - Fork 0
/
Models.txt
37 lines (28 loc) · 1.24 KB
/
Models.txt
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
List of Models for Game Learning
Model PPO -1
model = PPO('CnnPolicy', env, verbose=1, tensorboard_log=LOG_DIR, learning_rate=0.000001,
n_steps=512, seed = 311, gamma = 0.99)
Mario - PPO - 2
model = PPO('CnnPolicy', env, verbose=1, tensorboard_log=LOG_DIR, learning_rate=0.000001,
n_steps=512, seed = 121, gamma = 0.99)
Mario PPO - 3
model = PPO('CnnPolicy', env, verbose=1, tensorboard_log=LOG_DIR, learning_rate=0.000001,
n_steps=512, seed = 214, gamma = 0.99)
Mario PPO - 4
model = PPO('MlpPolicy', env, verbose=1, tensorboard_log=LOG_DIR, learning_rate=0.000001,
n_steps=512, seed =10 )
Mario PPO -5
model = PPO('CnnPolicy', env, verbose=1, tensorboard_log=LOG_DIR, learning_rate=0.000001,
n_steps=512, seed =20 )
Mario PPO -6
model = PPO('MlpPolicy', env, verbose=1, tensorboard_log=LOG_DIR, learning_rate=0.000001,
n_steps=512, seed =6 )
Mario PPO - 7
model = PPO('MlpPolicy', env, verbose=1, tensorboard_log=LOG_DIR, learning_rate=0.06000,
n_steps=512, seed =20 )
Mario DQN - 8
model = DQN('CnnPolicy', env, verbose=1, tensorboard_log=LOG_DIR, learning_rate=0.000001,
buffer_size=224, seed =10)
Mario A2C - 9
model = A2C('CnnPolicy', env, verbose=1, tensorboard_log=LOG_DIR, learning_rate=0.000001,
seed =20)