Skip to content

Include run_name in training logs for better run traceability #101

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 3 commits into
base: main
Choose a base branch
from
+6 −0
Open

Include run_name in training logs for better run traceability #101

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5a37688
Display run name during training in OnPolicyRunner
ShaoshuSu Jul 20, 2025
e9f0c67
Add name to CONTRIBUTORS.md
ShaoshuSu Jul 20, 2025
5309d00
Merge branch 'main' into feat/runname_display
ClemensSchwarke Nov 19, 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 CONTRIBUTORS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,5 +37,6 @@ Please keep the lists sorted alphabetically.
* Matthijs van der Boon
* Özhan Özen
* Pascal Roth
* Shaoshu Su
* Zhang Chong
* Ziqi Fan
5 changes: 5 additions & 0 deletions rsl_rl/runners/on_policy_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -238,10 +238,14 @@ def log(self, locs: dict, width: int = 80, pad: int = 35) -> None:

str = f" \033[1m Learning iteration {locs['it']}/{locs['tot_iter']} \033[0m "

run_name = self.cfg.get("run_name")
Copy link

@epalmaEth epalmaEth Nov 19, 2025

Choose a reason for hiding this comment

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

What about using --task for the run name instead of an additional --run_name parameter? Also i think we need to update the config example with the additional name.

Copy link
Collaborator

@ClemensSchwarke ClemensSchwarke Nov 19, 2025

Choose a reason for hiding this comment

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

run_name actually already exists. It is just the time stamp by default but can be passed as a CLI argument.

Copy link

@epalmaEth epalmaEth Nov 19, 2025 •
edited
Loading

Choose a reason for hiding this comment

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

Does it make sense to use run_name and not task still?

Copy link
Collaborator

@ClemensSchwarke ClemensSchwarke Nov 19, 2025

Choose a reason for hiding this comment

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

I think so because task would usually be the same for all your trainings. If you want to differentiate them you would need run_name.

run_name_string = f"""{"Run name:":>{pad}} {run_name}\n""" if run_name else ""

if len(locs["rewbuffer"]) > 0:
log_string = (
f"""{"#" * width}\n"""
f"""{str.center(width, " ")}\n\n"""
f"""{run_name_string}"""
f"""{"Computation:":>{pad}} {fps:.0f} steps/s (collection: {locs["collection_time"]:.3f}s, learning {
locs["learn_time"]:.3f}s)\n"""
f"""{"Mean action noise std:":>{pad}} {mean_std.item():.2f}\n"""
Expand All @@ -262,6 +266,7 @@ def log(self, locs: dict, width: int = 80, pad: int = 35) -> None:
log_string = (
f"""{"#" * width}\n"""
f"""{str.center(width, " ")}\n\n"""
f"""{run_name_string}"""
f"""{"Computation:":>{pad}} {fps:.0f} steps/s (collection: {locs["collection_time"]:.3f}s, learning {
locs["learn_time"]:.3f}s)\n"""
f"""{"Mean action noise std:":>{pad}} {mean_std.item():.2f}\n"""
Expand Down