Skip to content
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

fixes DQN run_n_episodes using the wrong environment variable #525

Merged
merged 2 commits into from
Jan 18, 2021
Merged

fixes DQN run_n_episodes using the wrong environment variable #525

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
55f650d
use argument variable instead of self variable
sidhantls Jan 18, 2021
e43ff17
chlog
Borda Jan 18, 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
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- Fixed the end of batch size mismatch ([#389](https://github.com/PyTorchLightning/pytorch-lightning-bolts/pull/389))
- Fixed `batch_size` parameter for DataModules remaining ([#344](https://github.com/PyTorchLightning/pytorch-lightning-bolts/pull/344))
- Fixed CIFAR `num_samples` ([#432](https://github.com/PyTorchLightning/pytorch-lightning-bolts/pull/432))
- Fixed DQN `run_n_episodes` using the wrong environment variable ([#525](https://github.com/PyTorchLightning/pytorch-lightning-bolts/pull/525))

## [0.2.5] - 2020-10-12

Expand Down
2 changes: 1 addition & 1 deletion pl_bolts/models/rl/dqn_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,7 +171,7 @@ def run_n_episodes(self, env, n_epsiodes: int = 1, epsilon: float = 1.0) -> List
while not done:
self.agent.epsilon = epsilon
action = self.agent(episode_state, self.device)
next_state, reward, done, _ = self.env.step(action[0])
next_state, reward, done, _ = env.step(action[0])
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

shall we also assign the env back, self.env = env?

Copy link
Contributor Author

@sidhantls sidhantls Jan 18, 2021 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

if we assign the test env to self.env in test_step, when training is done after testing, it'll use the test env (without seed) instead of what it was initialized with for training (env with seed)

episode_state = next_state
episode_reward += reward

Expand Down