def plot(self, y="return", x="learning_steps", save=False):
"""Plots the performance of the experiment
This function has only limited capabilities.
For more advanced plotting of results consider
:py:class:`Tools.Merger.Merger`.
"""
labels = rlpy.Tools.results.default_labels
performance_fig = plt.figure("Performance")
res = self.result
plt.plot(res[x], res[y], '-bo', lw=3, markersize=10)
plt.xlim(0, res[x][-1] * 1.01)
y_arr = np.array(res[y])
m = y_arr.min()
M = y_arr.max()
delta = M - m
if delta > 0:
plt.ylim(m - .1 * delta - .1, M + .1 * delta + .1)
xlabel = labels[x] if x in labels else x
ylabel = labels[y] if y in labels else y
plt.xlabel(xlabel, fontsize=16)
plt.ylabel(ylabel, fontsize=16)
if save:
path = os.path.join(
self.full_path,
"{:3}-performance.pdf".format(self.exp_id))
performance_fig.savefig(path, transparent=True, pad_inches=.1)
plt.ioff()
plt.show()
def plot(self, y="return", x="learning_steps", save=False):
"""Plots the performance of the experiment
This function has only limited capabilities.
For more advanced plotting of results consider
:py:class:`Tools.Merger.Merger`.
"""
labels = rlpy.Tools.results.default_labels
performance_fig = plt.figure("Performance")
res = self.result
plt.plot(res[x], res[y], '-bo', lw=3, markersize=10)
plt.xlim(0, res[x][-1] * 1.01)
y_arr = np.array(res[y])
m = y_arr.min()
M = y_arr.max()
delta = M - m
if delta > 0:
plt.ylim(m - .1 * delta - .1, M + .1 * delta + .1)
xlabel = labels[x] if x in labels else x
ylabel = labels[y] if y in labels else y
plt.xlabel(xlabel, fontsize=16)
plt.ylabel(ylabel, fontsize=16)
if save:
path = os.path.join(self.full_path,
"{:3}-performance.pdf".format(self.exp_id))
performance_fig.savefig(path, transparent=True, pad_inches=.1)
plt.ioff()
plt.show()
def showLearning(self, representation):
pi = np.zeros(
(self.X_discretization,
self.XDot_discretization),
'uint8')
V = np.zeros((self.X_discretization, self.XDot_discretization))
if self.valueFunction_fig is None:
self.valueFunction_fig = plt.figure("Value Function")
self.valueFunction_im = plt.imshow(
V,
cmap='ValueFunction',
interpolation='nearest',
origin='lower',
vmin=self.MIN_RETURN,
vmax=self.MAX_RETURN)
plt.xticks(self.xTicks, self.xTicksLabels, fontsize=12)
plt.yticks(self.yTicks, self.yTicksLabels, fontsize=12)
plt.xlabel(r"$x$")
plt.ylabel(r"$\dot x$")
self.policy_fig = plt.figure("Policy")
self.policy_im = plt.imshow(
pi,
cmap='MountainCarActions',
interpolation='nearest',
origin='lower',
vmin=0,
vmax=self.actions_num)
plt.xticks(self.xTicks, self.xTicksLabels, fontsize=12)
plt.yticks(self.yTicks, self.yTicksLabels, fontsize=12)
plt.xlabel(r"$x$")
plt.ylabel(r"$\dot x$")
plt.show()
for row, xDot in enumerate(np.linspace(self.XDOTMIN, self.XDOTMAX, self.XDot_discretization)):
for col, x in enumerate(np.linspace(self.XMIN, self.XMAX, self.X_discretization)):
s = [x, xDot]
Qs = representation.Qs(s, False)
As = self.possibleActions()
pi[row, col] = representation.bestAction(s, False, As)
V[row, col] = max(Qs)
self.valueFunction_im.set_data(V)
self.policy_im.set_data(pi)
self.valueFunction_fig = plt.figure("Value Function")
plt.draw()
self.policy_fig = plt.figure("Policy")
plt.draw()
def plot_trials(self,
y="eps_return",
x="learning_steps",
average=10,
save=False):
"""Plots the performance of the experiment
This function has only limited capabilities.
For more advanced plotting of results consider
:py:class:`Tools.Merger.Merger`.
"""
def movingaverage(interval, window_size):
window = np.ones(int(window_size)) / float(window_size)
return np.convolve(interval, window, 'same')
labels = rlpy.Tools.results.default_labels
performance_fig = plt.figure("Performance")
trials = self.trials
y_arr = np.array(trials[y])
if average:
assert type(average) is int, "Filter length is not an integer!"
y_arr = movingaverage(y_arr, average)
plt.plot(trials[x], y_arr, '-bo', lw=3, markersize=10)
plt.xlim(0, trials[x][-1] * 1.01)
m = y_arr.min()
M = y_arr.max()
delta = M - m
if delta > 0:
plt.ylim(m - .1 * delta - .1, M + .1 * delta + .1)
xlabel = labels[x] if x in labels else x
ylabel = labels[y] if y in labels else y
plt.xlabel(xlabel, fontsize=16)
plt.ylabel(ylabel, fontsize=16)
if save:
path = os.path.join(self.full_path,
"{:3}-trials.pdf".format(self.exp_id))
performance_fig.savefig(path, transparent=True, pad_inches=.1)
plt.ioff()
plt.show()
