def __init__(
self,
env_spec,
subsample_factor=1.,
num_seq_inputs=1,
regressor_args=None,
name='ContinuousMLPBaseline',
):
"""
Constructor.
:param env_spec: environment specification.
:param subsample_factor:
:param num_seq_inputs: number of sequence inputs.
:param regressor_args: regressor arguments.
"""
Parameterized.__init__(self)
Serializable.quick_init(self, locals())
super(ContinuousMLPBaseline, self).__init__(env_spec)
if regressor_args is None:
regressor_args = dict()
self._regressor = ContinuousMLPRegressor(
input_shape=(env_spec.observation_space.flat_dim *
num_seq_inputs, ),
output_dim=1,
name=name,
**regressor_args)
self.name = name
def test_fit_unnormalized(self):
cmr = ContinuousMLPRegressor(input_shape=(1, ),
output_dim=1,
normalize_inputs=False)
data = np.linspace(-np.pi, np.pi, 1000)
obs = [{'observations': [[x]], 'returns': [np.sin(x)]} for x in data]
observations = np.concatenate([p['observations'] for p in obs])
returns = np.concatenate([p['returns'] for p in obs])
for _ in range(150):
cmr.fit(observations, returns.reshape((-1, 1)))
paths = {
'observations': [[-np.pi], [-np.pi / 2], [-np.pi / 4], [0],
[np.pi / 4], [np.pi / 2], [np.pi]]
}
prediction = cmr.predict(paths['observations'])
expected = [[0], [-1], [-0.707], [0], [0.707], [1], [0]]
assert np.allclose(prediction, expected, rtol=0, atol=0.1)
x_mean = self.sess.run(cmr.model._networks['default'].x_mean)
x_mean_expected = np.zeros_like(x_mean)
x_std = self.sess.run(cmr.model._networks['default'].x_std)
x_std_expected = np.ones_like(x_std)
assert np.array_equal(x_mean, x_mean_expected)
assert np.array_equal(x_std, x_std_expected)
def __init__(
self,
env_spec,
subsample_factor=1.,
num_seq_inputs=1,
regressor_args=None,
name='ContinuousMLPBaseline',
):
"""
Continuous MLP Baseline.
It fits the input data by performing linear regression
to the outputs.
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 = ContinuousMLPRegressor(
input_shape=(env_spec.observation_space.flat_dim *
num_seq_inputs, ),
output_dim=1,
name=name,
**regressor_args)
self.name = name
def test_predict_sym(self, output_dim, input_shape):
cmr = ContinuousMLPRegressor(input_shape=input_shape,
output_dim=output_dim,
optimizer=LbfgsOptimizer,
optimizer_args=dict())
new_input_var = tf.compat.v1.placeholder(tf.float32,
shape=(None, ) + input_shape)
data = np.random.random(size=input_shape)
outputs = cmr.predict_sym(new_input_var, name='y_hat_sym')
y_hat_sym = self.sess.run(outputs, feed_dict={new_input_var: [data]})
y_hat = cmr._f_predict([data])
assert np.allclose(y_hat, y_hat_sym, rtol=0, atol=1e-5)
def __init__(self,
env_spec,
num_seq_inputs=1,
regressor_args=None,
name='ContinuousMLPBaseline'):
if regressor_args is None:
regressor_args = dict()
self._regressor = ContinuousMLPRegressor(
input_shape=(env_spec.observation_space.flat_dim *
num_seq_inputs, ),
output_dim=1,
name=name,
**regressor_args)
self.name = name
def test_is_pickleable(self):
cmr = ContinuousMLPRegressor(input_shape=(1, ), output_dim=1)
with tf.compat.v1.variable_scope(('ContinuousMLPRegressor/'
'NormalizedInputMLPModel'),
reuse=True):
bias = tf.compat.v1.get_variable('mlp/hidden_0/bias')
bias.load(tf.ones_like(bias).eval())
result1 = cmr.predict(np.ones((1, 1)))
h = pickle.dumps(cmr)
with tf.compat.v1.Session(graph=tf.Graph()):
cmr_pickled = pickle.loads(h)
result2 = cmr_pickled.predict(np.ones((1, 1)))
assert np.array_equal(result1, result2)
class ContinuousMLPBaseline(Baseline, Parameterized, Serializable):
"""A value function using a mlp network."""
def __init__(
self,
env_spec,
subsample_factor=1.,
num_seq_inputs=1,
regressor_args=None,
name='ContinuousMLPBaseline',
):
"""
Constructor.
:param env_spec: environment specification.
:param subsample_factor:
:param num_seq_inputs: number of sequence inputs.
:param regressor_args: regressor arguments.
"""
Parameterized.__init__(self)
Serializable.quick_init(self, locals())
super(ContinuousMLPBaseline, self).__init__(env_spec)
if regressor_args is None:
regressor_args = dict()
self._regressor = ContinuousMLPRegressor(
input_shape=(env_spec.observation_space.flat_dim *
num_seq_inputs, ),
output_dim=1,
name=name,
**regressor_args)
self.name = name
@overrides
def get_param_values(self, **tags):
"""Get parameter values."""
return self._regressor.get_param_values(**tags)
@overrides
def set_param_values(self, val, **tags):
"""Set parameter values to val."""
self._regressor.set_param_values(val, **tags)
@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_params_internal(self, **tags):
return self._regressor.get_params_internal(**tags)
class ContinuousMLPBaseline(Baseline):
"""A value function using a MLP network."""
def __init__(
self,
env_spec,
subsample_factor=1.,
num_seq_inputs=1,
regressor_args=None,
name='ContinuousMLPBaseline',
):
"""
Continuous MLP Baseline.
It fits the input data by performing linear regression
to the outputs.
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 = ContinuousMLPRegressor(
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 ContinuousMLPBaseline(Baseline):
"""A value function using a MLP network.
It fits the input data by performing linear regression
to the outputs.
Args:
env_spec (garage.envs.env_spec.EnvSpec): Environment specification.
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,
num_seq_inputs=1,
regressor_args=None,
name='ContinuousMLPBaseline'):
super().__init__(env_spec)
if regressor_args is None:
regressor_args = dict()
self._regressor = ContinuousMLPRegressor(
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.
Args:
paths (dict[numpy.ndarray]): 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 (dict[numpy.ndarray]): 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()
