Pith. sign in

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 1

years

2026 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Parameter Exploration for RLVR via Variational Learning

cs.LG · 2026-08-10 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Parameter Exploration for RLVR via Variational Learning cs.LG · 2026-08-10 · conditional · none · ref 3

    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.