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

Jump to bottom

[RLlib] SimpleQ PyTorch Multi GPU fix #26109

Merged
merged 11 commits into from
Jun 28, 2022
Merged

[RLlib] SimpleQ PyTorch Multi GPU fix #26109

Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
97a0d4e
test
ArturNiederfahrenhorst Jun 26, 2022
cf377f7
another test
ArturNiederfahrenhorst Jun 26, 2022
7f60cc1
next test
ArturNiederfahrenhorst Jun 26, 2022
59aad58
test only simpleQ
ArturNiederfahrenhorst Jun 26, 2022
a6c7909
raises device data as exception
ArturNiederfahrenhorst Jun 26, 2022
8cb5b60
only log
ArturNiederfahrenhorst Jun 26, 2022
fba6ca9
log in parallel grad calc
ArturNiederfahrenhorst Jun 26, 2022
2ce484f
log target model device
ArturNiederfahrenhorst Jun 26, 2022
c4a4258
place samplebatch on correct device
ArturNiederfahrenhorst Jun 26, 2022
40fdd54
possible fix
ArturNiederfahrenhorst Jun 26, 2022
bc47f1b
revert release tests folder
ArturNiederfahrenhorst Jun 26, 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
4 changes: 1 addition & 3 deletions rllib/algorithms/simple_q/simple_q_torch_policy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,9 +173,7 @@ def _compute_q_values(
self, model: ModelV2, obs_batch: TensorType, is_training=None
) -> TensorType:
_is_training = is_training if is_training is not None else False
input_dict = self._lazy_tensor_dict(
SampleBatch(obs=obs_batch, _is_training=_is_training)
)
input_dict = SampleBatch(obs=obs_batch, _is_training=_is_training)
# Make sure, everything is PyTorch tensors.
model_out, _ = model(input_dict, [], None)
return model_out