def value(self, obs):
obs = obs / 255.0
out = self.conv1(obs)
out = layers.pool2d(input=out,
pool_size=2,
pool_stride=2,
pool_type='max')
out = self.conv2(out)
out = layers.pool2d(input=out,
pool_size=2,
pool_stride=2,
pool_type='max')
out = self.conv3(out)
out = layers.pool2d(input=out,
pool_size=2,
pool_stride=2,
pool_type='max')
out = self.conv4(out)
out = layers.flatten(out, axis=1)
if self.algo == 'Dueling':
As = self.fc2_adv(self.fc1_adv(out))
V = self.fc2_val(self.fc1_val(out))
Q = As + (V - layers.reduce_mean(As, dim=1, keep_dim=True))
else:
Q = self.fc1(out)
return Q
def value(self, obs):
obs = obs / 255.0
out = self.conv1(obs)
out = layers.pool2d(input=out,
pool_size=2,
pool_stride=2,
pool_type='max',
data_format="NHWC")
out = self.conv2(out)
out = layers.pool2d(input=out,
pool_size=2,
pool_stride=2,
pool_type='max',
data_format="NHWC")
out = layers.flatten(out, axis=1)
Q = self.fc1(out)
return Q
def value(self, obs):
obs = obs / 255.0
# print(len(obs.shape))
# if len(obs.shape)>4:
# obs = layers.squeeze(input=obs,axes=[-1])
# obs = layers.squeeze(input=obs)
out = self.conv1(obs)
out = layers.pool2d(
input=out, pool_size=2, pool_stride=2, pool_type='max')
out = self.conv2(out)
out = layers.pool2d(
input=out, pool_size=2, pool_stride=2, pool_type='max')
out = self.conv3(out)
out = layers.pool2d(
input=out, pool_size=2, pool_stride=2, pool_type='max')
out = self.conv4(out)
out = layers.flatten(out, axis=1)
Q = self.fc1(out)
return Q
def value(self, obs):
out = self.conv1(obs)
out = layers.pool2d(input=out,
pool_size=2,
pool_stride=2,
pool_type='max')
out = self.conv2(out)
out = layers.pool2d(input=out,
pool_size=2,
pool_stride=2,
pool_type='max')
out = self.conv3(out)
out = layers.pool2d(input=out,
pool_size=2,
pool_stride=2,
pool_type='max')
out = self.conv4(out)
out = layers.flatten(out, axis=1)
Q = self.fc1(out)
return Q
def value(self, obs):
# obs = obs / 255.0
print('value', obs.shape)
out = self.conv1(obs)
out = layers.pool2d(input=out,
pool_size=4,
pool_stride=2,
pool_type='max')
# out = self.conv2(out)
# out = layers.pool2d(
# input=out, pool_size=2, pool_stride=2, pool_type='max')
# out = self.conv3(out)
# out = layers.pool2d(
# input=out, pool_size=2, pool_stride=2, pool_type='max')
# out = self.conv4(out)
out = layers.flatten(out, axis=1)
start = self.fc1(out)
start = paddle.fluid.layers.softmax(start)
end = self.fc2(out)
end = paddle.fluid.layers.softmax(end)
num = self.fc3(out)
vec = layers.concat([start, end, num], axis=1)
return vec
