class GaussianMLPBaseline(Baseline):
"""A value function using Gaussian MLP network."""
def __init__(
self,
env_spec,
subsample_factor=1.,
num_seq_inputs=1,
regressor_args=None,
name='GaussianMLPBaseline',
):
"""
Gaussian MLP Baseline with Model.
It fits the input data to a gaussian distribution estimated by
a MLP.
Args:
env_spec (garage.envs.env_spec.EnvSpec): Environment specification.
subsample_factor (float): The factor to subsample the data. By
default it is 1.0, which means using all the data.
num_seq_inputs (float): Number of sequence per input. By default
it is 1.0, which means only one single sequence.
regressor_args (dict): Arguments for regressor.
"""
super().__init__(env_spec)
if regressor_args is None:
regressor_args = dict()
self._regressor = GaussianMLPRegressor(
input_shape=(env_spec.observation_space.flat_dim *
num_seq_inputs, ),
output_dim=1,
name=name,
**regressor_args)
self.name = name
def fit(self, paths):
"""Fit regressor based on paths."""
observations = np.concatenate([p['observations'] for p in paths])
returns = np.concatenate([p['returns'] for p in paths])
self._regressor.fit(observations, returns.reshape((-1, 1)))
def predict(self, path):
"""Predict value based on paths."""
return self._regressor.predict(path['observations']).flatten()
def get_param_values(self, **tags):
"""Get parameter values."""
return self._regressor.get_param_values(**tags)
def set_param_values(self, flattened_params, **tags):
"""Set parameter values to val."""
self._regressor.set_param_values(flattened_params, **tags)
def get_params_internal(self, **tags):
"""Get internal parameters."""
return self._regressor.get_params_internal(**tags)
class MultiTaskGaussianMLPBaseline(Baseline, Parameterized):
"""A value function using gaussian mlp network."""
def __init__(
self,
env_spec,
extra_dims=0,
subsample_factor=1.,
num_seq_inputs=1,
regressor_args=None,
):
"""
Constructor.
:param env_spec:
:param subsample_factor:
:param num_seq_inputs:
:param regressor_args:
"""
Serializable.quick_init(self, locals())
super(MultiTaskGaussianMLPBaseline, self).__init__(env_spec)
if regressor_args is None:
regressor_args = dict()
self._regressor = GaussianMLPRegressor(
input_shape=((env_spec.observation_space.flat_dim + extra_dims) *
num_seq_inputs, ),
output_dim=1,
name="vf",
use_trust_region=True,
**regressor_args)
@overrides
def fit(self, paths):
"""Fit regressor based on paths."""
observations = np.concatenate([p["observations"] for p in paths])
tasks = np.concatenate([p["tasks_gt"] for p in paths])
latents = np.concatenate([p["latents"] for p in paths])
aug_obs = np.concatenate([observations, tasks, latents], axis=1)
returns = np.concatenate([p["returns"] for p in paths])
self._regressor.fit(aug_obs, returns.reshape((-1, 1)))
@overrides
def predict(self, path):
"""Predict value based on paths."""
inputs = np.concatenate(
(path["observations"], path["tasks_gt"], path["latents"]), axis=1)
return self._regressor.predict(inputs, ).flatten()
@overrides
def get_param_values(self, **tags):
"""Get parameter values."""
return self._regressor.get_param_values(**tags)
@overrides
def set_param_values(self, flattened_params, **tags):
"""Set parameter values to val."""
self._regressor.set_param_values(flattened_params, **tags)
class GaussianMLPBaseline(Baseline, Parameterized, Serializable):
"""A value function using gaussian mlp network."""
def __init__(
self,
env_spec,
subsample_factor=1.,
num_seq_inputs=1,
regressor_args=None,
name="GaussianMLPBaseline",
):
"""
Constructor.
:param env_spec:
:param subsample_factor:
:param num_seq_inputs:
:param regressor_args:
"""
Parameterized.__init__(self)
Serializable.quick_init(self, locals())
super(GaussianMLPBaseline, self).__init__(env_spec)
if regressor_args is None:
regressor_args = dict()
self._regressor = GaussianMLPRegressor(
input_shape=(env_spec.observation_space.flat_dim *
num_seq_inputs, ),
output_dim=1,
name=name,
**regressor_args)
self.name = name
@overrides
def fit(self, paths):
"""Fit regressor based on paths."""
observations = np.concatenate([p["observations"] for p in paths])
returns = np.concatenate([p["returns"] for p in paths])
self._regressor.fit(observations, returns.reshape((-1, 1)))
@overrides
def predict(self, path):
"""Predict value based on paths."""
return self._regressor.predict(path["observations"]).flatten()
@overrides
def get_param_values(self, **tags):
"""Get parameter values."""
return self._regressor.get_param_values(**tags)
@overrides
def set_param_values(self, flattened_params, **tags):
"""Set parameter values to val."""
self._regressor.set_param_values(flattened_params, **tags)
@overrides
def get_params_internal(self, **tags):
return self._regressor.get_params_internal(**tags)
class GaussianMLPBaseline(Baseline):
"""Gaussian MLP Baseline with Model.
It fits the input data to a gaussian distribution estimated by
a MLP.
Args:
env_spec (garage.envs.env_spec.EnvSpec): Environment specification.
subsample_factor (float): The factor to subsample the data. By
default it is 1.0, which means using all the data.
num_seq_inputs (float): Number of sequence per input. By default
it is 1.0, which means only one single sequence.
regressor_args (dict): Arguments for regressor.
name (str): Name of baseline.
"""
def __init__(
self,
env_spec,
subsample_factor=1.,
num_seq_inputs=1,
regressor_args=None,
name='GaussianMLPBaseline',
):
super().__init__(env_spec)
if regressor_args is None:
regressor_args = dict()
self._regressor = GaussianMLPRegressor(
input_shape=(env_spec.observation_space.flat_dim *
num_seq_inputs, ),
output_dim=1,
name=name,
subsample_factor=subsample_factor,
**regressor_args)
self.name = name
def fit(self, paths):
"""Fit regressor based on paths.
Args:
paths (list[dict]): Sample paths.
"""
observations = np.concatenate([p['observations'] for p in paths])
returns = np.concatenate([p['returns'] for p in paths])
self._regressor.fit(observations, returns.reshape((-1, 1)))
def predict(self, path):
"""Predict value based on paths.
Args:
path (list[dict]): Sample paths.
Returns:
numpy.ndarray: Predicted value.
"""
return self._regressor.predict(path['observations']).flatten()
def get_param_values(self):
"""Get parameter values.
Returns:
List[np.ndarray]: A list of values of each parameter.
"""
return self._regressor.get_param_values()
def set_param_values(self, flattened_params):
"""Set param values.
Args:
flattened_params (np.ndarray): A numpy array of parameter values.
"""
self._regressor.set_param_values(flattened_params)
def get_params_internal(self):
"""Get the params, which are the trainable variables.
Returns:
List[tf.Variable]: A list of trainable variables in the current
variable scope.
"""
return self._regressor.get_params_internal()
class CollisionAwareBaseline(Baseline, Parameterized):
"""A value function using gaussian mlp network."""
def __init__(
self,
env_spec,
subsample_factor=1.,
num_seq_inputs=1,
regressor_args=None,
):
"""
Constructor.
:param env_spec:
:param subsample_factor:
:param num_seq_inputs:
:param regressor_args:
"""
Parameterized.__init__(self)
Serializable.quick_init(self, locals())
Baseline.__init__(self, env_spec)
if regressor_args is None:
regressor_args = dict()
self._regressor = GaussianMLPRegressor(
input_shape=((env_spec.observation_space.flat_dim + 1) *
num_seq_inputs, ),
output_dim=1,
name="Baseline",
**regressor_args)
@overrides
def fit(self, paths):
"""Fit regressor based on paths."""
observations = np.concatenate([p["observations"] for p in paths])
collisions = np.concatenate(
np.float32([p["env_infos"]["in_collision"] for p in paths]))
collisions = np.expand_dims(collisions, axis=1)
aug_obs = np.concatenate([observations, collisions], axis=1)
returns = np.concatenate([p["returns"] for p in paths])
self._regressor.fit(aug_obs, returns.reshape((-1, 1)))
@overrides
def predict(self, path):
"""Predict value based on paths."""
collisions = np.expand_dims(path["env_infos"]["in_collision"], axis=1)
inputs = np.concatenate([path["observations"], collisions], axis=1)
return self._regressor.predict(inputs, ).flatten()
@overrides
def get_param_values(self, **tags):
"""Get parameter values."""
return self._regressor.get_param_values(**tags)
@overrides
def set_param_values(self, flattened_params, **tags):
"""Set parameter values to val."""
self._regressor.set_param_values(flattened_params, **tags)
@overrides
def get_params_internal(self, **tags):
return self._regressor.get_params_internal(**tags)
