Cuzyoung 00602df9e9 feat(slow-update): add config-controlled gated / force-injected modes ...

Add optimizer.slow_update_gate_with_selection to control how epoch-boundary
slow-update guidance is applied:
- false (default): force-injected - inject guidance into current & best
  unconditionally (unchanged behavior).
- true: gated - evaluate the slow-update candidate on the selection set and
  accept/reject via the same validation gate as step-level updates
  (logic follows the SkillReflection ablation).

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

2026-05-31 02:02:23 +00:00

..

__init__.py

refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update

2026-05-24 19:15:10 +00:00

clip.py

refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update

2026-05-24 19:15:10 +00:00

lr_autonomous.py

refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update

2026-05-24 19:15:10 +00:00

meta_skill.py

feat(slow-update): add config-controlled gated / force-injected modes

2026-05-31 02:02:23 +00:00

rewrite.py

refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update

2026-05-24 19:15:10 +00:00

scheduler.py

SkillOpt v0.1.0: initial release

2026-05-21 17:22:04 +00:00

select.py

SkillOpt v0.1.0: initial release

2026-05-21 17:22:04 +00:00

skill.py

refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update

2026-05-24 19:15:10 +00:00

slow_update.py

feat(slow-update): add config-controlled gated / force-injected modes

2026-05-31 02:02:23 +00:00

update_modes.py

SkillOpt v0.1.0: initial release

2026-05-21 17:22:04 +00:00