def __init__(self,
*,
env_spec,
common_network_cls,
common_network_args,
state_input_dim,
state_network_cls=None,
state_network_args=dict(),
action_network_cls=None,
action_network_args=dict()):
Serializable.quick_init(self, locals())
logger.log('Reconciler: {}'.format(locals()))
self.env_spec = env_spec
if state_network_cls is not None:
state_network_args[
'input_shape'] = env_spec.observation_space.shape
state_network = state_network_cls(**state_network_args)
self.state_input_layer = state_network.input_layer
state_processed_layer = state_network.output_layer
else:
self.state_input_layer = L.InputLayer(shape=(None,
state_input_dim),
input_var=None,
name='input_state')
state_processed_layer = self.state_input_layer
if action_network_cls is not None:
action_network_args['input_shape'] = (
env_spec.action_space.flat_dim, )
action_network = action_network_cls(**action_network_args)
self.action_input_layer = action_network.input_layer
action_processed_layer = action_network.output_layer
else:
self.action_input_layer = L.InputLayer(
shape=(None, env_spec.action_space.flat_dim),
input_var=None,
name='input_action')
action_processed_layer = self.action_input_layer
concat_layer = L.concat(
[L.flatten(state_processed_layer), action_processed_layer])
common_network_args['input_layer'] = concat_layer
common_network = common_network_cls(**common_network_args)
self.output_layer = common_network.output_layer
self.output_layers = [self.output_layer]
def __init__(self, name, input_shape, extra_input_shape, output_dim, hidden_sizes,
conv_filters, conv_filter_sizes, conv_strides, conv_pads,
extra_hidden_sizes=None,
hidden_W_init=L.XavierUniformInitializer(), hidden_b_init=tf.zeros_initializer,
output_W_init=L.XavierUniformInitializer(), output_b_init=tf.zeros_initializer,
hidden_nonlinearity=tf.nn.relu,
output_nonlinearity=None,
input_var=None, input_layer=None):
Serializable.quick_init(self, locals())
if extra_hidden_sizes is None:
extra_hidden_sizes = []
with tf.variable_scope(name):
input_flat_dim = np.prod(input_shape)
extra_input_flat_dim = np.prod(extra_input_shape)
total_input_flat_dim = input_flat_dim + extra_input_flat_dim
if input_layer is None:
l_in = L.InputLayer(shape=(None, total_input_flat_dim), input_var=input_var, name="input")
else:
l_in = input_layer
l_conv_in = L.reshape(
L.SliceLayer(
l_in,
indices=slice(input_flat_dim),
name="conv_slice"
),
([0],) + input_shape,
name="conv_reshaped"
)
l_extra_in = L.reshape(
L.SliceLayer(
l_in,
indices=slice(input_flat_dim, None),
name="extra_slice"
),
([0],) + extra_input_shape,
name="extra_reshaped"
)
l_conv_hid = l_conv_in
for idx, conv_filter, filter_size, stride, pad in zip(
range(len(conv_filters)),
conv_filters,
conv_filter_sizes,
conv_strides,
conv_pads,
):
l_conv_hid = L.Conv2DLayer(
l_conv_hid,
num_filters=conv_filter,
filter_size=filter_size,
stride=(stride, stride),
pad=pad,
nonlinearity=hidden_nonlinearity,
name="conv_hidden_%d" % idx,
)
l_extra_hid = l_extra_in
for idx, hidden_size in enumerate(extra_hidden_sizes):
l_extra_hid = L.DenseLayer(
l_extra_hid,
num_units=hidden_size,
nonlinearity=hidden_nonlinearity,
name="extra_hidden_%d" % idx,
W=hidden_W_init,
b=hidden_b_init,
)
l_joint_hid = L.concat(
[L.flatten(l_conv_hid, name="conv_hidden_flat"), l_extra_hid],
name="joint_hidden"
)
for idx, hidden_size in enumerate(hidden_sizes):
l_joint_hid = L.DenseLayer(
l_joint_hid,
num_units=hidden_size,
nonlinearity=hidden_nonlinearity,
name="joint_hidden_%d" % idx,
W=hidden_W_init,
b=hidden_b_init,
)
l_out = L.DenseLayer(
l_joint_hid,
num_units=output_dim,
nonlinearity=output_nonlinearity,
name="output",
W=output_W_init,
b=output_b_init,
)
self._l_in = l_in
self._l_out = l_out
LayersPowered.__init__(self, [l_out], input_layers=[l_in])
def __init__(self,
name,
input_shape,
extra_input_shape,
output_dim,
hidden_sizes,
conv_filters,
conv_filter_sizes,
conv_strides,
conv_pads,
extra_hidden_sizes=None,
hidden_W_init=L.XavierUniformInitializer(),
hidden_b_init=tf.zeros_initializer(),
output_W_init=L.XavierUniformInitializer(),
output_b_init=tf.zeros_initializer(),
hidden_nonlinearity=tf.nn.relu,
output_nonlinearity=None,
input_var=None,
input_layer=None):
Serializable.quick_init(self, locals())
if extra_hidden_sizes is None:
extra_hidden_sizes = []
with tf.variable_scope(name):
input_flat_dim = np.prod(input_shape)
extra_input_flat_dim = np.prod(extra_input_shape)
total_input_flat_dim = input_flat_dim + extra_input_flat_dim
if input_layer is None:
l_in = L.InputLayer(shape=(None, total_input_flat_dim),
input_var=input_var,
name="input")
else:
l_in = input_layer
l_conv_in = L.reshape(L.SliceLayer(l_in,
indices=slice(input_flat_dim),
name="conv_slice"),
([0], ) + input_shape,
name="conv_reshaped")
l_extra_in = L.reshape(L.SliceLayer(l_in,
indices=slice(
input_flat_dim, None),
name="extra_slice"),
([0], ) + extra_input_shape,
name="extra_reshaped")
l_conv_hid = l_conv_in
for idx, conv_filter, filter_size, stride, pad in zip(
range(len(conv_filters)),
conv_filters,
conv_filter_sizes,
conv_strides,
conv_pads,
):
l_conv_hid = L.Conv2DLayer(
l_conv_hid,
num_filters=conv_filter,
filter_size=filter_size,
stride=(stride, stride),
pad=pad,
nonlinearity=hidden_nonlinearity,
name="conv_hidden_%d" % idx,
)
l_extra_hid = l_extra_in
for idx, hidden_size in enumerate(extra_hidden_sizes):
l_extra_hid = L.DenseLayer(
l_extra_hid,
num_units=hidden_size,
nonlinearity=hidden_nonlinearity,
name="extra_hidden_%d" % idx,
W=hidden_W_init,
b=hidden_b_init,
)
l_joint_hid = L.concat(
[L.flatten(l_conv_hid, name="conv_hidden_flat"), l_extra_hid],
name="joint_hidden")
for idx, hidden_size in enumerate(hidden_sizes):
l_joint_hid = L.DenseLayer(
l_joint_hid,
num_units=hidden_size,
nonlinearity=hidden_nonlinearity,
name="joint_hidden_%d" % idx,
W=hidden_W_init,
b=hidden_b_init,
)
l_out = L.DenseLayer(
l_joint_hid,
num_units=output_dim,
nonlinearity=output_nonlinearity,
name="output",
W=output_W_init,
b=output_b_init,
)
self._l_in = l_in
self._l_out = l_out
LayersPowered.__init__(self, [l_out], input_layers=[l_in])
