AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

PlannerRFT: Reinforcing Diffusion Planners through Closed-Loop and Sample-Efficient Fine-Tuning

Hongchen Li, Tianyu Li, Jiazhi Yang, Mingyang Shang, Gaoqiang Wu, Caojun Wang, Haochen Tian, Zengrong Lin, Zhihui Hao, XianPeng Lang, Jia Hu, Hongyang Li

CVPR 2026 · Reinforcement learning › RL from feedback · approach: RL fine-tuning of generative models · 9 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
reinforcement fine-tune with policy-guided denoising and GRPOIL-pretrained Diffusion Planner · Test14-hard (reactive)nuPlan score: 69.22 -> 72.21Improved
reinforcement fine-tuningIL-pretrained Diffusion Planner · Val14 (reactive)nuPlan score: 82.80 -> 84.46Improved
reinforcement fine-tuningIL-pretrained Diffusion Planner · Val14 (non-reactive)nuPlan score: 89.87 -> 89.96No clear effect
reinforcement fine-tuningIL-pretrained Diffusion Planner · Test14-hard (non-reactive)nuPlan score: 75.99 -> 77.16Improved
add learned adaptive exploration policy (ablation)PlannerRFT · Test14-hard (reactive)R-score: 70.65 -> 72.21 vs fixed Beta; 65.82 vs uniformImproved
add classifier guidance without learned policy (uniform scales) (ablation)IL-pretrained planner RFT · Test14-hard (reactive)R-score: 68.83 -> 65.82Hurt
add guidance with fixed Beta distribution (ablation)RFT without guidance · Test14-hard (reactive)R-score: 68.83 -> 70.65Improved
fine-tune on Lt90 instead of Fail only (ablation)PlannerRFT · Test14-hard (reactive)nuPlan score: 63.75 -> 72.21Improved
fine-tune on Lt90 instead of All scenarios (ablation)PlannerRFT · Test14-hard (reactive)nuPlan score: 70.43 -> 72.21Improved
use RL instead of imitation fine-tuning on Lt90 (ablation)Diffusion Planner · Test14-hard (reactive)nuPlan score: 67.55 -> 72.21Improved
use survival reward instead of terminal reward (ablation)PlannerRFT · Test14-hard (reactive)nuPlan score: 71.59 -> 72.21Improved
lengthen reward horizon from 2 s to 4 s (ablation)PlannerRFT · Test14-hard (reactive)nuPlan score: 70.10 -> 72.21Improved

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