AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

Reward Model Evaluation via Automatically-Ranked Policy Alignment

Aoran Wang, Lei Ou, Yang Yu, Zongzhang Zhang

AAAI 2026 · Reinforcement learning › RL from feedback · approach: Theory of RLHF · 1 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
generate ranked policies with DGPI instead of noisy BC perturbations (ablation)PPAC · DoorKeyPotentialShaped score: 0.91 -> 0.98Improved
generate ranked policies with DGPI instead of noisy BC perturbations (ablation)PPAC · HalfCheetahSecondGoal-Slight score: 0.8346 -> 0.7549Mixed
generate ranked policies with DGPI instead of AIL checkpoints (ablation)PPAC · HalfCheetahSecondGoal-Slight/Intense score: 0.9774 -> 0.7549; 0.9549 -> 0.5203Improved
generate ranked policies with DGPI instead of AIL checkpoints (ablation)PPAC · DoorKeySecondGoal-Intense score: 0.6220 -> 0.4800Mixed
use listwise policy ranking (PPAC) instead of pairwise trajectory preference (TAC)PPAC · DoorKeySecondGoal-Intense score: 1.0000 -> 0.4800Improved
use PPAC instead of NegativeSTARC for PotentialShapedPPAC · HalfCheetahPotentialShaped vs GroundTruth equality: STARC 0.0000 vs -0.6745; PPAC 0.9873 vs 0.9873Improved

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