Generating rollouts from multiple weight-perturbed versions of the policy, pooled inside a GRPO group, improves RLVR performance over standard GRPO on math and code benchmarks.
Learning to explore with parameter-space noise: A deep dive into parameter-space noise for reinforcement learning with verifiable rewards.CoRR, abs/2602.02555, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Parameter Exploration for RLVR via Variational Learning
Generating rollouts from multiple weight-perturbed versions of the policy, pooled inside a GRPO group, improves RLVR performance over standard GRPO on math and code benchmarks.