agent_func、reward_func时--normalization_reward参数不起作用，对吗
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 28/100
- Issue type
- Documentation
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- python
- Domain
- machine-learning
Research direction
Trace where the --normalization_reward argument is parsed and where reward/value normalization is actually applied in the training loop, then check whether that path is reached when agent_func or reward_func is used and no critic model exists. The issue names no files, so first locate the argument/config definitions and the advantage or value computation that consumes the flag. Done means a confirmed answer stating whether normalization_reward behaves as normalization_value and requires a critic model, and updating the docs or comments if the current wording misleads users.
Written by the indexing model from the issue text.
Description
agent_func、reward_func时--normalization_reward参数不起作用，对吗
我是否也可以理解为normalization_reward其实是normalization_value，只有包含critic model时才生效
- Dominant language
- Python
- Stars
- 10.1k
- Forks
- 1k
- Avg merge
- 5h 19m
- Merged PRs (30d)
- 4
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from OpenRLHF/OpenRLHF
-
\fbox{} answers never extract — math reward is always 0 for fbox responsesPossibly taken @dhvani7014 claimed this 2 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 1 day
-
PPO critic averages LR and grad-norm telemetry across training stepsPossibly taken @Madhustat claimed this 14 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 30/100
Maintainers usually reply within 1 day
-
Difficulty 4/5 3-5 days Newbie friendliness 40/100
Maintainers usually reply within 1 day
-
math_utils.grade_answer ignores units when both reference and prediction carry one, so the right number with the wrong unit (or wrong rate) is graded correctPossibly taken @MaybeIcanShow claimed this 21 days ago. Open
Difficulty 3/5 Half a day Newbie friendliness 35/100
Maintainers usually reply within 1 day
-
Suboptimal forward dispatch order in make_experience causes unnecessary serializationPossibly taken @RainieLLM claimed this 28 days ago. Open
Difficulty 3/5 1-2 days Newbie friendliness 28/100
OpenRLHF/OpenRLHF#1358 · 1 comment ·
Maintainers usually reply within 1 day
All issues in OpenRLHF/OpenRLHF
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
noontide-co/mainbranch#1211 · 1 comment ·
Maintainers usually reply within 1 day
-
[1.x Bug] run-operation --sql reports success but rolls back writes on transaction-capable adaptersOpentriage
Difficulty 2/5 1-3 hours Newbie friendliness 64/100
dbt-labs/dbt#16784 · 1 comment ·
Maintainers usually reply within 1 day
-
bug needs-triage
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
Maintainers usually reply within 1 day
-
bug settings ui
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
DewaldOosthuizen/py-tray-command-launcher#162 ·
Maintainers usually reply within 1 day
-
run_all sleeps after the final job despite documenting delays between jobsPossibly taken @Gambit-Checkmate claimed this today. Open
Difficulty 2/5 1-3 hours Newbie friendliness 74/100