def fit_model(self,
state_list,
action_list,
win_in,
verbose=True,
max_iter=1000):
"""
Fits a Gaussian Process model to the state / action pairs passed in.
This creates a model of the environment which is used during
policy optimization instead of querying the environment directly.
See mxfusion.gp_modules for additional types of GP models to fit,
including Sparse GP and Stochastic Varitional Inference Sparse GP.
"""
X, Y = self.prepare_data(state_list, action_list, win_in)
m = Model()
m.N = Variable()
m.X = Variable(shape=(m.N, X.shape[-1]))
m.noise_var = Variable(shape=(1, ),
transformation=PositiveTransformation(),
initial_value=0.01)
m.kernel = RBF(input_dim=X.shape[-1],
variance=1,
lengthscale=1,
ARD=True)
m.Y = GPRegression.define_variable(X=m.X,
kernel=m.kernel,
noise_var=m.noise_var,
shape=(m.N, Y.shape[-1]))
m.Y.factor.gp_log_pdf.jitter = 1e-6
infr = GradBasedInference(
inference_algorithm=MAP(model=m, observed=[m.X, m.Y]))
infr.run(X=mx.nd.array(X),
Y=mx.nd.array(Y),
max_iter=max_iter,
learning_rate=0.1,
verbose=verbose)
return m, infr, X, Y
def make_gpregr_model(self, lengthscale, variance, noise_var):
from mxfusion.models import Model
from mxfusion.components.variables import Variable, PositiveTransformation
from mxfusion.modules.gp_modules import GPRegression
from mxfusion.components.distributions.gp.kernels import RBF
dtype = 'float64'
m = Model()
m.N = Variable()
m.X = Variable(shape=(m.N, 3))
m.noise_var = Variable(transformation=PositiveTransformation(),
initial_value=mx.nd.array(noise_var,
dtype=dtype))
kernel = RBF(input_dim=3,
ARD=True,
variance=mx.nd.array(variance, dtype=dtype),
lengthscale=mx.nd.array(lengthscale, dtype=dtype),
dtype=dtype)
m.Y = GPRegression.define_variable(X=m.X,
kernel=kernel,
noise_var=m.noise_var,
shape=(m.N, 1),
dtype=dtype)
return m