Skip to content

DQN tutorial fixes #2026

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

Merged
merged 4 commits into from
Sep 6, 2022
Merged

DQN tutorial fixes #2026

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
00acd8d
gym website domain change
SiftingSands Sep 5, 2022
37dd008
fixed issues due to changes to gym's API
SiftingSands Sep 5, 2022
e5169eb
no more warnings other than using cartpole v0
SiftingSands Sep 5, 2022
cf2e13a
Merge branch 'master' into DQN_fix
Sep 6, 2022
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
10 changes: 5 additions & 5 deletions intermediate_source/reinforcement_q_learning.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,14 +6,14 @@


This tutorial shows how to use PyTorch to train a Deep Q Learning (DQN) agent
on the CartPole-v0 task from the `OpenAI Gym <https://www.gymlibrary.ml/>`__.
on the CartPole-v0 task from the `OpenAI Gym <https://www.gymlibrary.dev/>`__.

**Task**

The agent has to decide between two actions - moving the cart left or
right - so that the pole attached to it stays upright. You can find an
official leaderboard with various algorithms and visualizations at the
`Gym website <https://www.gymlibrary.ml/environments/classic_control/cart_pole>`__.
`Gym website <https://www.gymlibrary.dev/environments/classic_control/cart_pole>`__.

.. figure:: /_static/img/cartpole.gif
:alt: cartpole
Expand Down Expand Up @@ -74,7 +74,7 @@
import torchvision.transforms as T


env = gym.make('CartPole-v0').unwrapped
env = gym.make('CartPole-v0', new_step_api=True, render_mode='single_rgb_array').unwrapped

# set up matplotlib
is_ipython = 'inline' in matplotlib.get_backend()
Expand Down Expand Up @@ -254,7 +254,7 @@ def get_cart_location(screen_width):
def get_screen():
# Returned screen requested by gym is 400x600x3, but is sometimes larger
# such as 800x1200x3. Transpose it into torch order (CHW).
screen = env.render(mode='rgb_array').transpose((2, 0, 1))
screen = env.render().transpose((2, 0, 1))
# Cart is in the lower half, so strip off the top and bottom of the screen
_, screen_height, screen_width = screen.shape
screen = screen[:, int(screen_height*0.4):int(screen_height * 0.8)]
Expand Down Expand Up @@ -461,7 +461,7 @@ def optimize_model():
for t in count():
# Select and perform an action
action = select_action(state)
_, reward, done, _ = env.step(action.item())
_, reward, done, _, _ = env.step(action.item())
reward = torch.tensor([reward], device=device)

# Observe new state
Expand Down