def nature_cnn_v2(unscaled_images, **conv_kwargs):
scaled_images = tf.cast(unscaled_images, tf.float32) / 255.
activ = tf.nn.relu
h = activ(
conv(scaled_images,
'c1',
nf=32,
rf=8,
stride=4,
init_scale=np.sqrt(2),
**conv_kwargs))
h2 = activ(
conv(h,
'c2',
nf=64,
rf=4,
stride=2,
init_scale=np.sqrt(2),
**conv_kwargs))
out = activ(
conv(h2,
'c3',
nf=64,
rf=3,
stride=1,
init_scale=np.sqrt(2),
**conv_kwargs))
h3 = conv_to_fc(out)
return activ(fc(h3, 'fc1', nh=512,
init_scale=np.sqrt(2))), tf.layers.flatten(out)
def __init__(self,
env,
observations,
latent,
f_features,
estimate_q=False,
vf_latent=None,
sess=None,
**tensors):
self.Xs = observations
self.X = observations[1]
self.f_features = f_features
self.state = tf.constant([])
self.initial_state = None
self.__dict__.update(tensors)
vf_latent = vf_latent if vf_latent is not None else latent
vf_latent = tf.layers.flatten(vf_latent)
latent = tf.layers.flatten(latent)
# Based on the action space, will select what probability distribution type
self.pdtype = make_pdtype(env.action_space)
self.pd, self.pi = self.pdtype.pdfromlatent(latent, init_scale=0.01)
# Take an action
self.action = self.pd.sample()
# Calculate the neg log of our probability
self.neglogp = self.pd.neglogp(self.action)
self.sess = sess or tf.get_default_session()
if estimate_q:
assert isinstance(env.action_space, gym.spaces.Discrete)
self.q = fc(vf_latent, 'q', env.action_space.n)
self.vf = self.q
else:
self.vf = fc(vf_latent, 'vf', 1)
self.vf = self.vf[:, 0]
def fc_func(x):
return fc(x,
'mlp_fc{}'.format(i),
nh=num_hidden,
init_scale=np.sqrt(2))
def h4_func(x):
return activ(fc(x, 'fc1', nh=512, init_scale=np.sqrt(2)))