Skip to content

[RLlib] Also tag set_state #57651

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
+7 −6
Open

[RLlib] Also tag set_state #57651

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
9095e62
Use tags to track set_state calls when setting weights
ArturNiederfahrenhorst Oct 12, 2025
7292300
Merge branch 'master' into set_state_w_tags
ArturNiederfahrenhorst Oct 12, 2025
d1653c9
tag sample_get_state_and_metrics
ArturNiederfahrenhorst Oct 12, 2025
c947169
add func
ArturNiederfahrenhorst Oct 12, 2025
d97c6af
remove fire and forget
ArturNiederfahrenhorst Oct 12, 2025
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 rllib/algorithms/impala/impala.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -801,6 +801,7 @@ def _sample_and_get_connector_states(self):
if num_healthy_remote_workers > 0:
async_results = self.env_runner_group.foreach_env_runner_async_fetch_ready(
func="sample_get_state_and_metrics",
tag="sample_get_state_and_metrics",
Copy link
Contributor Author

Choose a reason for hiding this comment

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

Not the reason for this PR, just an addition I picked up on the way.

timeout_seconds=self.config.timeout_s_sampler_manager,
return_obj_refs=False,
return_actor_ids=True,
Expand Down
12 changes: 6 additions & 6 deletions rllib/env/env_runner_group.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -557,12 +557,12 @@ def sync_env_runner_states(
env_runner_states.update(rl_module_state)

# Broadcast updated states back to all workers.
self.foreach_env_runner(
"set_state", # Call the `set_state()` remote method.
self.foreach_env_runner_async_fetch_ready(
func="set_state",
tag="set_state",
kwargs=dict(state=env_runner_states),
remote_worker_ids=env_runner_indices_to_update,
local_env_runner=False,
timeout_seconds=0.0, # This is a state update -> Fire-and-forget.
timeout_seconds=0.0,
)

def foreach_env_runner_async_fetch_ready(
Expand Down Expand Up @@ -708,10 +708,10 @@ def sync_weights(
rl_module_state_ref = ray.put(rl_module_state)

# Sync to specified remote workers in this EnvRunnerGroup.
self.foreach_env_runner(
self.foreach_env_runner_async_fetch_ready(
func="set_state",
tag="set_state",
kwargs=dict(state=rl_module_state_ref),
local_env_runner=False, # Do not sync back to local worker.
remote_worker_ids=to_worker_indices,
timeout_seconds=timeout_seconds,
)
Expand Down