deepspeedai / deepspeedai/DeepSpeed

[REQUEST] Does PPO requires a critic that backpropagates?

Open
#3,446 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
Python
Stars
43.1k
Forks
5k
Avg merge
4d 15h
Merged PRs (30d)
112

Description

Is your feature request related to a problem? Please describe.
I wondered whether a critic model is necessary for DeepSpeedPPOTrainer in ppo_trainer.py located at applications/DeepSpeed-Chat/training/step3_rlhf_finetuning/ppo_trainer.py. It seem that self.critic_model in the code has nothing to do with the training justing backpropagating.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading applications/DeepSpeed-Chat/training/step3_rlhf_finetuning/ppo_trainer.py, focusing on DeepSpeedPPOTrainer and every use of self.critic_model. Trace whether it participates in training or backpropagation, then determine and document whether PPO requires it; done means the critic's role and required behavior are unambiguous.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.