-
-
Notifications
You must be signed in to change notification settings - Fork 20
Add new actions and improves handling of stochastic actions #449
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.
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
Shaobo-Zhou
wants to merge
62
commits into
munich-quantum-toolkit:main
Choose a base branch
from
Shaobo-Zhou:new_structure
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Add new actions and improves handling of stochastic actions #449
Shaobo-Zhou
wants to merge
62
commits into
munich-quantum-toolkit:main
from
Shaobo-Zhou:new_structure
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Update action space and feature space Update actions Update action space
Fix: resolve pre-commit issues and add missing annotations Fix: resolve pre-commit issues and add missing annotations Remove example_test.py Remove example_test.py
Fix: resolve pre-commit issues and add missing annotations Fix: resolve pre-commit issues and add missing annotations Fix: resolve pre-commit issues and add missing annotations
Signed-off-by: Shaobo-Zhou <[email protected]>
Fix windows runtime warning problem Fix windows runtime warning issue
7644681
to
44e0e40
Compare
985671d
to
350bae5
Compare
154b25c
to
91208d1
Compare
7f5f521
to
622d409
Compare
Hey @Shaobo-Zhou, we just merged #468 to fix the CI on |
denialhaag
requested changes
Sep 25, 2025
This seems to have worked fine! I just had two quick points regarding the rebase. 🙂 |
5ccc3c0
to
b28ccf2
Compare
5614a9f
to
fa008a6
Compare
48c7aa8
to
0c98e56
Compare
268e947
to
34a1c7c
Compare
99c7847
to
a8d069a
Compare
8987453
to
114b79b
Compare
07ec60f
to
aaf14b1
Compare
Signed-off-by: Shaobo-Zhou <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR introduces new actions to the reinforcement learning environment and adds support for stochastic mapping passes:
🚀 Major Changes
Expanded Action Space
AIRouting
as a routing/mapping option and wrapped inSafeAIRouting
for stable integration into the RL pipeline.GraphPlacement
andNoiseAwarePlacement
(fidelity-aware).Support for Stochastic Passes
AIRouting
,SabreLayout
) in a multi-trial evaluation loop, optimizing for the figure of merit instead of the default gate count internally in Qiskit passes.max_iterations
as parameters to control trial counts, enabling improved predictor performance and stability.**Changes in
determine_valid_actions_for_state**
Fixes and Enhancements
OptimizeCliffords
by ensuringCollectCliffords
runs beforehand.reward.py
GatesInBasis
inrl/predictorenv.py
INDEP
intest_predictor_rl.py
, since the current action space does not guarantee support for high-level gates._posixsubprocess
issues.Dependency Update
qiskit-ibm-ai-local-transpiler
to the dependenciesnetworkx==2.8.5
to ensure compatibility withqiskit-ibm-ai-local-transpiler
pytket_qiskit>=0.71.0
Checklist: