AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

Rate or Fate? RLV$^{\varepsilon}$R: Reinforcement Learning with Verifiable Noisy Rewards

Ali Rad, Khashayar Filom, Darioush Keivan, Peyman Mohajerin Esfahani, Ehsan Kamalinejad

ICML 2026 · Reinforcement learning › RL from feedback · approach: Scaling RL with verifiable rewards · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
verifier with positive Youden index J>0 versus J<0 in GRPO (ablation)Qwen2.5-3B GRPO on code · OpenR1 code validationpass@1: J=1.0: +8.0%; J=-0.1: -12.6% vs baseImproved
raise verifier quality J from 0.3 to 0.7 to 1.0 (ablation)Qwen2.5-3B GRPO on code · OpenR1 code validationpass@1: 16.0% -> 18.6% -> 20.8% (J 0.3, 0.7, 1.0)Improved
use zero-informative verifier J=0 (ablation)Qwen2.5-3B GRPO on code · OpenR1 code validationpass@1: +0.6%No clear effect
high false-positive noise instead of high false-negative noise at fixed J=0.3 (ablation)Qwen2.5-3B GRPO on code · OpenR1 code validationpass@1: 16.0% -> 14.6%Hurt
anti-aligned verifier J=-0.1 (ablation)Qwen2.5-3B GRPO on code · OpenR1 code validationpass@1: 13.4% (J=0) -> 0.16%Hurt
PPO with noisy verifier, J>0 versus J=0 versus J<0 (ablation)DeepSeek-LLM-7B-chat PPO · GSM8Kvalidation accuracy: about 24% -> 63-64% for J>0; 21-22% for J~0; 1-3% for J<0Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy