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

[RLlib] Get rid of experimental_relax_shapes #29214

Merged
merged 3 commits into from
Jan 31, 2023
Merged

[RLlib] Get rid of experimental_relax_shapes #29214

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
3361d85
initial
ArturNiederfahrenhorst Oct 11, 2022
33f0f79
Merge branch 'master' into tfdeprecation
ArturNiederfahrenhorst Nov 30, 2022
80eac51
Merge branch 'master' into tfdeprecation
ArturNiederfahrenhorst Jan 5, 2023
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
8 changes: 4 additions & 4 deletions rllib/policy/eager_tf_policy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,7 +180,7 @@ def compute_actions_from_input_dict(
tf.function(
super(TracedEagerPolicy, self)._compute_actions_helper,
autograph=False,
experimental_relax_shapes=True,
reduce_retracing=True,
)
)
self._traced_compute_actions_helper = True
Expand All @@ -206,7 +206,7 @@ def learn_on_batch(self, samples):
tf.function(
super(TracedEagerPolicy, self)._learn_on_batch_helper,
autograph=False,
experimental_relax_shapes=True,
reduce_retracing=True,
)
)
self._traced_learn_on_batch_helper = True
Expand All @@ -226,7 +226,7 @@ def compute_gradients(self, samples: SampleBatch) -> ModelGradients:
tf.function(
super(TracedEagerPolicy, self)._compute_gradients_helper,
autograph=False,
experimental_relax_shapes=True,
reduce_retracing=True,
)
)
self._traced_compute_gradients_helper = True
Expand All @@ -246,7 +246,7 @@ def apply_gradients(self, grads: ModelGradients) -> None:
tf.function(
super(TracedEagerPolicy, self)._apply_gradients_helper,
autograph=False,
experimental_relax_shapes=True,
reduce_retracing=True,
)
)
self._traced_apply_gradients_helper = True
Expand Down