AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

FlowMAP: Flow Matching for Generalizable Agent Planning

Jiarun Fu, Lizhong Ding, Ye Yuan, Qiuning Wei, Zhaohuan Linghu, Yurong Cheng, Changsheng Li, Tianlong Gu, Liang Chang, Guoren Wang

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing

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 planning-time flow (VTFM) on top of the RL backbone (ablation)FlowMAP · Minecraft (Diamond)episodic return: 6.0 ± 0.4 -> 9.0 ± 0.2Improved
add value-transport flow matching to the consistency regularizer (ablation)FlowMAP · Minecraft (Diamond)episodic return: 6.2 ± 0.4 -> 9.0 ± 0.2Improved
add the consistency term to the RL baseline (ablation)RL-only baseline · Minecraft (Diamond)episodic return: 6.0 ± 0.4 -> 6.2 ± 0.4Improved
use value-shaped target instead of uniform target (ablation)FlowMAP · Minecraft (Diamond)episodic return: 6.5 ± 0.5 -> 9.0 ± 0.2Improved
use distributional transport instead of pointwise value ascent (ablation)FlowMAP · Minecraft (Diamond)episodic return: 6.7 ± 0.4 -> 9.0 ± 0.2Improved
add consistency loss to VTFM (ablation)FlowMAP · Minecraft (Diamond)episodic return: 7.1 ± 0.6 -> 9.0 ± 0.2Improved
co-train the flow with the policy instead of freezing it (ablation)FlowMAP · Minecraft (Diamond)episodic return: 7.6 ± 0.3 -> 9.0 ± 0.2Improved
add planning-time flow (VTFM) on top of the RL backbone (ablation)FlowMAP · BSuitemean episodic return: 54.2 -> 69.0Improved
add value-transport flow matching to the consistency regularizer (ablation)FlowMAP · BSuitemean episodic return: 55.5 -> 69.0Improved
use value-shaped target instead of uniform target (ablation)FlowMAP · BSuitemean episodic return: 53.8 -> 69.0Improved
use distributional transport instead of pointwise value ascent (ablation)FlowMAP · BSuitemean episodic return: 61.3 -> 69.0Improved
add consistency loss to VTFM (ablation)FlowMAP · BSuitemean episodic return: 57.8 -> 69.0Improved

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