✨ Add RL truncation#697
Draft
flowerthrower wants to merge 32 commits into
Draft
Conversation
## Description This PR addresses critical bugs in the RL training process with the following key changes: **Structure Improvements:** - **Redesigned action validation logic** (`predictorenv.py`): Rewrote `determine_valid_actions_for_state()` with a more structured (but equivalent) state machine that explicitly tracks three circuit states (synthesized, laid_out, routed) and handles 6 different state combinations. - Added helper methods `is_circuit_laid_out()` and `is_circuit_routed()` to replace the buggy `CheckMap` pass with more reliable state checking. The new logic supports both the original restricted MDP and a flexible general MDP mode. - **Fixed type annotation** (`actions.py`): Corrected `do_while` parameter type from `dict[str, Circuit]` to `PropertySet` and added missing import for Qiskit's `PropertySet`. - **Added reproducibility** (`predictor.py`): Set random seed for non-test training runs to ensure reproducible results. - **Improved VF2Layout error handling** (`predictorenv.py`): Replaced assertion failures with warning logs when VF2Layout doesn't find a solution, preventing crashes during training. **Test Updates:** - Suppressed deprecation warnings in tket routing test --------- Signed-off-by: Patrick Hopf <81010725+flowerthrower@users.noreply.github.com> Co-authored-by: flowerthrower <flowerthrower@users.noreply.github.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
…ove-action-pass-imports-and-wrappers
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
tbd
Fixes #678
Assisted-by: GPT-5.5 via Codex
Checklist
If PR contains AI-assisted content:
Assisted-by: [Model Name] via [Tool Name]footer.