Add curriculum description, both reasoning and execution manual.#53
Conversation
|
Warning Review limit reached
More reviews will be available in 45 minutes and 1 second. Learn how PR review limits work. Your organization has run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After more reviews become available, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available. Please see our Fair Usage Limits Policy for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (3)
📝 WalkthroughWalkthroughThis PR introduces formal curriculum documentation for a scheduling RL task. A new curriculum rationale document defines the target deferral policy, learning challenges, and six-stage progression strategy. A companion operator runbook provides practical training instructions with stage-specific configurations. README links are updated to point to both documents. ChangesCurriculum Documentation
🎯 2 (Simple) | ⏱️ ~10 minutes 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@curriculum_setup.md`:
- Around line 228-239: Resolve the inconsistency between curriculum_setup.md and
curriculum_argument.md for "Stage E: Main Arrivals + Noisy Logic Prices" by
choosing one of the three fixes and applying it consistently: (A) mark Stage E
as optional/experimental in both documents by adding an explicit
"Optional/Experimental" label and a short justification and keep the placeholder
in curriculum_setup.md if you intend it optional; (B) if you intend Stage E as
required, remove the "usually skipped" remark and fill in the missing
stage-specific arguments in curriculum_setup.md (replace "[fill in
noisy-logic-price setup]" with the full noisy-logic-price configuration and
example commands) and update curriculum_argument.md to assert it is part of the
formal progression; or (C) retain it as optional but complete the specification
and add a clear "experimental/optional" notice in both files; ensure the
phrasing for "Stage E" is identical in curriculum_setup.md and
curriculum_argument.md so operators see the same status and provide the
noisy-logic-price setup snippet under the Stage E heading if you choose to keep
the stage runnable.
- Line 206: The sentence "Note: I trained on `2.0`, but staged scaling such as
`1.0 -> 2.0` is also possible." uses first-person voice; change it to an
operator-manual tone by rephrasing to something like "Trained on `2.0`; staged
scaling such as `1.0 -> 2.0` is also supported." Replace the original string
with this neutral phrasing in the curriculum_setup.md line where that note
appears to keep tone consistent with the rest of the document.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 77d43f95-97b4-4024-91ae-caf4602aeac5
📒 Files selected for processing (3)
README.mdcurriculum_argument.mdcurriculum_setup.md
| # --job-arrival-scale [SCALE] | ||
| ``` | ||
|
|
||
| Note: I trained on `2.0`, but staged scaling such as `1.0 -> 2.0` is also possible. |
There was a problem hiding this comment.
Replace first-person note with operator-manual voice.
The informal first-person phrasing "I trained on 2.0" is inconsistent with the rest of the document's operator-manual tone.
📝 Suggested rewording
-Note: I trained on `2.0`, but staged scaling such as `1.0 -> 2.0` is also possible.
+Note: Example scale values include `2.0` or staged scaling such as `1.0 -> 2.0`.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@curriculum_setup.md` at line 206, The sentence "Note: I trained on `2.0`, but
staged scaling such as `1.0 -> 2.0` is also possible." uses first-person voice;
change it to an operator-manual tone by rephrasing to something like "Trained on
`2.0`; staged scaling such as `1.0 -> 2.0` is also supported." Replace the
original string with this neutral phrasing in the curriculum_setup.md line where
that note appears to keep tone consistent with the rest of the document.
| ## Stage E: Main Arrivals + Noisy Logic Prices (Optional) | ||
|
|
||
| Goal: keep the learned policy while adding moderate price irregularity. | ||
|
|
||
| Comment: This stage is usually skipped. Another run with higher job scale is often used instead. | ||
| The idea remains valid, but at the moment it does not change much in practice. | ||
|
|
||
| ### Stage-specific arguments | ||
|
|
||
| ```bash | ||
| # [fill in noisy-logic-price setup] | ||
| ``` |
There was a problem hiding this comment.
Resolve Stage E curriculum inconsistency between documents.
curriculum_argument.md presents Stage E ("Main Arrivals + Noisy Logic Prices") as part of the formal intended 6-stage progression (lines 118-120: "This stage adds robustness..."), but curriculum_setup.md states it is "usually skipped" (line 232) and "does not change much in practice" (line 233).
This creates ambiguity for operators: the rationale document presents E as a necessary robustness step, while the execution guide recommends skipping it.
Additionally, the stage-specific arguments remain incomplete (line 238: "[fill in noisy-logic-price setup]"), which compounds the confusion.
Recommendation: Either (1) update curriculum_argument.md to acknowledge Stage E as optional with limited practical value, or (2) complete the Stage E specification here and remove the "usually skipped" disclaimer, or (3) clearly mark Stage E as "experimental/optional" in both documents with consistent language.
🧰 Tools
🪛 LanguageTool
[style] ~233-~233: For conciseness, consider replacing this expression with an adverb.
Context: ...ed instead. The idea remains valid, but at the moment it does not change much in practice. #...
(AT_THE_MOMENT)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@curriculum_setup.md` around lines 228 - 239, Resolve the inconsistency
between curriculum_setup.md and curriculum_argument.md for "Stage E: Main
Arrivals + Noisy Logic Prices" by choosing one of the three fixes and applying
it consistently: (A) mark Stage E as optional/experimental in both documents by
adding an explicit "Optional/Experimental" label and a short justification and
keep the placeholder in curriculum_setup.md if you intend it optional; (B) if
you intend Stage E as required, remove the "usually skipped" remark and fill in
the missing stage-specific arguments in curriculum_setup.md (replace "[fill in
noisy-logic-price setup]" with the full noisy-logic-price configuration and
example commands) and update curriculum_argument.md to assert it is part of the
formal progression; or (C) retain it as optional but complete the specification
and add a clear "experimental/optional" notice in both files; ensure the
phrasing for "Stage E" is identical in curriculum_setup.md and
curriculum_argument.md so operators see the same status and provide the
noisy-logic-price setup snippet under the Stage E heading if you choose to keep
the stage runnable.
2 participants
No description provided.