def _get_DQN_prediction(self, image):
""" image: [0,255]"""
#image = image / 255.0
with argscope(Conv2D, nl=PReLU.f, use_bias=True):
l = Conv2D('conv0', image, out_channel=32, kernel_shape=5)
l = MaxPooling('pool0', l, 2)
l = Conv2D('conv1', l, out_channel=32, kernel_shape=5)
l = MaxPooling('pool1', l, 2)
l = Conv2D('conv2', l, out_channel=64, kernel_shape=4)
l = MaxPooling('pool2', l, 2)
l = Conv2D('conv3', l, out_channel=64, kernel_shape=3)
l = FullyConnected('fc0',
l,
512,
nl=lambda x, name: LeakyReLU.f(x, 0.01, name))
# the original arch
#.Conv2D('conv0', image, out_channel=32, kernel_shape=8, stride=4)
#.Conv2D('conv1', out_channel=64, kernel_shape=4, stride=2)
#.Conv2D('conv2', out_channel=64, kernel_shape=3)
if not DUELING:
Q = FullyConnected('fct', l, NUM_ACTIONS, nl=tf.identity)
else:
V = FullyConnected('fctV', l, 1, nl=tf.identity)
As = FullyConnected('fctA', l, NUM_ACTIONS, nl=tf.identity)
Q = tf.add(As, V - tf.reduce_mean(As, 1, keep_dims=True))
return tf.identity(Q, name='Qvalue')
def _get_DQN_prediction(self, image):
""" image: [0,255]"""
image = image / 255.0
with argscope(Conv2D, nl=PReLU.f, use_bias=True):
return (
LinearWrap(image).Conv2D(
'conv0', out_channel=32,
kernel_shape=5).MaxPooling('pool0', 2).Conv2D(
'conv1', out_channel=32, kernel_shape=5).MaxPooling(
'pool1', 2).Conv2D('conv2',
out_channel=64,
kernel_shape=4).MaxPooling(
'pool2',
2).Conv2D('conv3',
out_channel=64,
kernel_shape=3)
# the original arch
#.Conv2D('conv0', image, out_channel=32, kernel_shape=8, stride=4)
#.Conv2D('conv1', out_channel=64, kernel_shape=4, stride=2)
#.Conv2D('conv2', out_channel=64, kernel_shape=3)
.FullyConnected('fc0',
512,
nl=lambda x, name: LeakyReLU.f(x, 0.01, name)
).FullyConnected('fct',
NUM_ACTIONS,
nl=tf.identity)())
def _get_DQN_prediction(self, image):
#TODO: Do we need to add other pre-processing? e.g., subtract mean
image = image / 255.0
#TODO: The network structure can be improved?
with argscope(Conv2D, nl=tf.nn.relu,
use_bias=True): # Activation for each layer
l = Conv2D('conv0', image, out_channel=32, kernel_shape=5)
l = MaxPooling('pool0', l, 2)
l = Conv2D('conv1', l, out_channel=32, kernel_shape=5)
l = MaxPooling('pool1', l, 2)
l = Conv2D('conv2', l, out_channel=64, kernel_shape=4)
l = MaxPooling('pool2', l, 2)
l = Conv2D('conv2', l, out_channel=64, kernel_shape=3)
# the original arch
# .Conv2D('conv0', image, out_channel=32, kernel_shape=8, stride=4)
# .Conv2D('conv1', out_channel=64, kernel_shape=4, stride=2)
# .Conv2D('conv2', out_channel=64, kernel_shape=3)
l = FullyConnected('fc0',
l,
512,
nl=lambda x, name: LeakyReLU.f(x, 0.01, name))
l = FullyConnected('fct', l, NUM_ACTIONS, nl=tf.identity())