Skip to content

Ode integrators + bump pytorch to > 0.4.1 #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 5 commits into
base: master
Choose a base branch
from
Open

Ode integrators + bump pytorch to > 0.4.1 #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
2dfba6d
Added midpoint and runge kutta integrators
juancamilog Sep 14, 2018
9e47045
avoid runtineerror by falling back to encoding variance
juancamilog Sep 14, 2018
b7268b8
updates for pytorch >= support
juancamilog Mar 4, 2021
d871bf8
further updates for pytorch >= 0.4.1
juancamilog Mar 4, 2021
0146f82
make clamp no in place
juancamilog Mar 4, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 13 additions & 25 deletions examples/cartpole.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,12 +35,7 @@ def plot_loss(J_hist):
plt.show(block=False)


def plot_path(Z,
encoding=ENCODING,
indices=None,
reality=None,
std_scale=1.0,
legend=True):
def plot_path(Z, encoding=ENCODING, indices=None, reality=None, std_scale=1.0, legend=True):
if not PLOT:
return

Expand Down Expand Up @@ -75,18 +70,12 @@ def plot_path(Z,

for i in range(1, 4):
j = std_scale * i
plt.gca().fill_between(
t.flat, (mean - j * std).flat, (mean + j * std).flat,
color=colors[index],
alpha=1.0 / (i + 1))
plt.gca().fill_between(t.flat, (mean - j * std).flat, (mean + j * std).flat,
color=colors[index],
alpha=1.0 / (i + 1))

if legend:
plt.legend(
bbox_to_anchor=(0.0, 1.0, 1.0, 0.7),
loc="upper left",
ncol=4,
mode="expand",
borderaxespad=0.)
plt.legend(bbox_to_anchor=(0.0, 1.0, 1.0, 0.7), loc="upper left", ncol=4, mode="expand", borderaxespad=0.)

plt.xlim(0, N)
plt.axhline(0, linestyle="--", color="#333333", linewidth=0.25)
Expand Down Expand Up @@ -152,15 +141,14 @@ def on_iteration(iteration, state, Z, U, J_opt):
)

controller.train()
Z, U, state = controller.fit(
U,
encoding=ENCODING,
n_iterations=50,
on_iteration=on_iteration,
on_trial=on_trial,
max_trials=20,
u_min=UMIN,
u_max=UMAX)
Z, U, state = controller.fit(U,
encoding=ENCODING,
n_iterations=50,
on_iteration=on_iteration,
on_trial=on_trial,
max_trials=20,
u_min=UMIN,
u_max=UMAX)

plt.figure()
plot_loss(J_hist)
Expand Down
354 changes: 226 additions & 128 deletions notebooks/known_dynamics/cartpole.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

364 changes: 332 additions & 32 deletions notebooks/known_dynamics/double_cartpole.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

429 changes: 275 additions & 154 deletions notebooks/known_dynamics/pendulum.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

111 changes: 80 additions & 31 deletions notebooks/known_dynamics/rendezvous.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

Loading