AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Reinforced Refinement With Self-Aware Expansion for End-to-End Autonomous Driving

Haochen Liu, Tianyu Li, Haohan Yang, Li Chen, Caojun Wang, Ke Guo, Haochen Tian, H. Y. Li, Hongyang Li, Chen Lv

TPAMI 2026 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 22 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
add GRPO cost constraints to IL (ablation)Hydra-MDP refinement · NAVSIM navtestPDMS: 87.0 -> 89.3 (+2.3)Improved
RL refinement without IL objective (ablation)Hydra-MDP refinement · NAVSIM navtestPDMS: 87.0 -> 87.9 (+0.9)No clear effect
add IL objective to GRPO cost and RL (ablation)R2SE-MDP · NAVSIM navtestPDMS: 87.9 -> 89.7 (+1.8)Improved
add self-aware expansion mechanism (ablation)R2SE-MDP · NAVSIM navtestPDMS: 89.7 -> 91.6 (+1.9)Improved
loosen hard case threshold to epsilon=10 (ablation)R2SE-MDP · NAVSIM navtestPDMS: 91.6 -> 90.9 (-0.7)Hurt
train with only 500 hard cases (epsilon 0.45, PDMS=0) (ablation)R2SE-MDP · NAVSIM navtestPDMS: 91.2 (+4.7)Improved
replace GPD tail model with power law (ablation)R2SE expansion · NAVSIM navtestPDMS: -0.5 PDMS, -0.6 EPHurt
replace GPD tail model with KDE (ablation)R2SE expansion · NAVSIM navtestPDMS: -2.0 PDMSHurt
replace GPD tail model with percentile (ablation)R2SE expansion · NAVSIM navtestPDMS: -5.0 EP and -5.7 PDMSHurt
set expansion confidence sigma to 0.05 instead of 0.75 (ablation)R2SE expansion · NAVSIM navtestPDMS: -1.5Hurt
set expansion confidence sigma to 0.95 instead of 0.75 (ablation)R2SE expansion · NAVSIM navtestPDMS: -1.3Hurt
add R2SE to VAD on hardest 20% Bench2Drive scenariosVAD · Bench2Drive hard scenariosDS: +21.31 DS, +29.22 route completionImproved

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