#######
# GMR #
#######
gmm = GMM(n_components=4)
gmm.from_samples(data)
#x0 = 0
x0 = 1.5
#y0 = 1.5
y0 = -1.5
z0 = np.squeeze(
gmm.predict(np.array([0, 1]),
np.array([x0, y0])[np.newaxis, :]))
dxdy = np.squeeze(
gmm.condition_derivative(np.array([0, 1]), np.array([x0, y0])))
print('z( %g, %g ):' % (x0, y0), z0)
print('dydx( %g, %g ):' % (x0, y0), dxdy)
Zp = np.zeros_like(Zr)
for i, x in enumerate(x_scale):
for j, y in enumerate(y_scale):
Zp[j][i] = np.squeeze(
gmm.predict(np.array([0, 1]),
np.array([x, y])[np.newaxis, :]))
#########
# PLOTS #
#########
#azim = -120 ; elev = 40
df = df.drop([name + ' s2' for name in features_to_drop], axis=1)
s_sprime_indices = np.array(
list(range(dim_s)) + list(range(dim_s + dim_a, dim_t)))
s_a_indices = np.array(range(dim_s + dim_a))
delta_a = []
grad_a = []
delta_s_norm = []
for _, samp in tqdm(df.iterrows(), total=len(df), leave=False):
s_a = samp[state_1 + actions].to_numpy()[np.newaxis, :]
s_sprime = samp[state_1 + state_2].to_numpy()
sprime = samp[state_2].to_numpy()
expected_sprime = gmm.predict(s_a_indices, s_a)
grad_a_sprime = gmm.condition_derivative(s_sprime_indices,
s_sprime)[:, dim_s:]
delta_a.append(grad_a_sprime.dot((expected_sprime - sprime).T))
#if 'grad_a_prev' in globals() :
#grad_a.append( grad_a_sprime - grad_a_prev )
#grad_a_prev = grad_a_sprime
grad_a.append(grad_a_sprime)
delta_s_norm.append(np.linalg.norm(expected_sprime - sprime))
fig, ax = plt.subplots(2, 1, sharex=True)
fig.canvas.set_window_title('Policy corrections')
ax[0].set_title('Trial result')
ax[0].plot(df[actions])
ax[0].legend(['Steering rate', 'Boggie torque'])
s = covariance.ravel()
plt.fill_between(X_test, y - s, y + s, alpha=0.2)
plt.plot(X_test, y, lw=2)
n_samples = 100
X = np.ndarray((n_samples, 2))
X[:, 0] = np.linspace(0, 2 * np.pi, n_samples)
X[:, 1] = np.sin(X[:, 0]) + random_state.randn(n_samples) * 0.1
gmm = GMM(n_components=3, random_state=0)
gmm.from_samples(X)
Y = gmm.predict(np.array([0]), X_test[:, np.newaxis])
#x = 1.5
x = 1.65
#x = 3
y = np.squeeze( gmm.predict(np.array([0]), np.array([ x ])[np.newaxis,:] ) )
dxdy = np.squeeze( gmm.condition_derivative( np.array([0]), np.array([ x ]) ) )
print( 'y( %g ):' % x, y )
print( 'dydx( %g ):' % x, dxdy )
plt.subplot(1, 2, 2)
plt.title("Mixture of Experts: $p(Y | X) = \Sigma_k \pi_{k, Y|X} "
"\mathcal{N}_{k, Y|X}$")
plt.scatter(X[:, 0], X[:, 1])
plot_error_ellipses(plt.gca(), gmm, colors=["r", "g", "b"])
plt.plot(X_test, Y.ravel(), c="k", lw=2)
d = 0.5
plt.plot( [ x - d, x + d ], [ y - dxdy*d, y + dxdy*d ] )
plt.show()
