CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning
CorrGRPO normalizes multi-reward GRPO with Pearson correlations so large rewards do not drown smaller signals.
1 stories, newest first · one card per story
CorrGRPO normalizes multi-reward GRPO with Pearson correlations so large rewards do not drown smaller signals.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views