PPO vs DPO vs GRPO: which RL method should you use?
Pick by the signal you have: preference pairs mean DPO, a checker you can run in code means GRPO, a learned reward model means PPO. Memory and cost math inside.
dpo
1 post with the tag “dpo”
Pick by the signal you have: preference pairs mean DPO, a checker you can run in code means GRPO, a learned reward model means PPO. Memory and cost math inside.