A new reward reshaping method provably increases reward variance for GRPO-based RLHF training, with an O(n log n) global optimization algorithm and preliminary speedups in experiments.
Busa-Fekete, B
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Accelerating RLHF Training with Reward Variance Increase
A new reward reshaping method provably increases reward variance for GRPO-based RLHF training, with an O(n log n) global optimization algorithm and preliminary speedups in experiments.