passdrill
AI & LLM Engineering · Fine-tuning & Model Customisation · Card 010/010 easy

DeepSeekMath's training pipeline (Shao et al.) uses a reinforcement-learning algorithm called Group Relative Policy Optimization (GRPO) instead of standard PPO to reduce the memory cost of the RL stage. What specific change does GRPO make to how the advantage used in the policy update is computed, compared to standard PPO?

  1. GRPO still trains a separate learned value/critic network exactly as PPO does, and its only change from PPO is removing the separate reward model used to score outputs
  2. GRPO uses a single fixed baseline value, chosen once by hand before training begins and never recomputed, in place of PPO's learned value function for every prompt across the entire training run
  3. GRPO requires a human-labeled preference judgment for every one of the sampled outputs before it can compute any output's advantage, replacing PPO's learned value function with direct human scoring
  4. GRPO removes PPO's separate learned value/critic network entirely; for a given prompt it samples a group of outputs from the current policy, uses that group's own average reward as a baseline, and computes each output's advantage as how far its reward deviates from that group's baseline, normalized by the group's reward variability
Next card → Shuffle