Hybrid GRPO averages tanh-transformed multi-sample rewards with a bootstrapped value baseline to estimate advantages, but the preprint provides no in-paper evidence that it outperforms PPO or GRPO.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Hybrid Group Relative Policy Optimization: A Multi-Sample Approach to Enhancing Policy Optimization
Hybrid GRPO averages tanh-transformed multi-sample rewards with a bootstrapped value baseline to estimate advantages, but the preprint provides no in-paper evidence that it outperforms PPO or GRPO.