Skip to content

Keras lr

環境設定

1
2
3
!pip install keras-rl
!pip install pyvirtualdisplay
!apt-get install xvfb

Virtual Displayの設定

1
2
3
4
5
6
# Start virtual display
from pyvirtualdisplay import Display
display = Display(visible=0, size=(1024, 768))
display.start()
import os
os.environ["DISPLAY"] = ":" + str(display.display) + "." + str(display.screen)

Cartpoleのサンプル

 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
import numpy as np
import gym

from keras.models import Sequential
from keras.layers import Dense, Activation, Flatten
from keras.optimizers import Adam

from rl.agents.dqn import DQNAgent
from rl.policy import BoltzmannQPolicy
from rl.memory import SequentialMemory

from gym import wrappers

ENV_NAME = 'CartPole-v0'

# Get the environment and extract the number of actions.
env = gym.make(ENV_NAME)
env = wrappers.Monitor(env, './', force=True) # save animations

np.random.seed(123)
env.seed(123)
nb_actions = env.action_space.n

# Next, we build a very simple model.
model = Sequential()
model.add(Flatten(input_shape=(1,) + env.observation_space.shape))
model.add(Dense(16))
model.add(Activation('relu'))
model.add(Dense(16))
model.add(Activation('relu'))
model.add(Dense(16))
model.add(Activation('relu'))
model.add(Dense(nb_actions))
model.add(Activation('linear'))
print(model.summary())

# Finally, we configure and compile our agent. You can use every built-in Keras optimizer and
# even the metrics!
memory = SequentialMemory(limit=50000, window_length=1)
policy = BoltzmannQPolicy()
dqn = DQNAgent(model=model, nb_actions=nb_actions, memory=memory, nb_steps_warmup=10,
               target_model_update=1e-2, policy=policy)
dqn.compile(Adam(lr=1e-3), metrics=['mae'])

dqn.fit(env, nb_steps=50000, visualize=False, verbose=2)

# After training is done, we save the final weights.
dqn.save_weights('dqn_{}_weights.h5f'.format(ENV_NAME), overwrite=True)

# Finally, evaluate our algorithm for 5 episodes.
#dqn.test(env, nb_episodes=5, visualize=True, nb_max_episode_steps=300)

動画の作成

1
2
3
4
5
6
# download videos
from google.colab import files
import glob

for file in glob.glob("*.mp4"):
  files.download(file)