Practice free →
HomeClaudeaifoundationsinstructgpt_rlhf › The PPO objective includes a KL penalty against …

The PPO objective includes a KL penalty against the SFT model to

AReduce the memory footprint of the RL step
BEncourage longer responses to user prompts
CMitigate over-optimisation of the reward model
DSpeed up convergence of the policy gradient
Answer & Solution
Correct answer: C. Mitigate over-optimisation of the reward model
Without the KL term, the policy can find degenerate outputs that game the RM (reward hacking). Pulling the policy toward the SFT distribution at every token keeps generations sane.
Solve this in the app — Claude practice & 24k+ MCQs →
Related questions