AI Paper Atlas

Research map / Reinforcement learning / Offline RL

One-Step Flow Q-Learning: Addressing the Diffusion Policy Bottleneck in Offline Reinforcement Learning

Thanh Xuan Nguyen, Chang D. Yoo

ICLR 2026 · Reinforcement learning › Offline RL · approach: Diffusion models for offline decision making · 5 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
train and evaluate fully in one-step regime with average velocity (OFQL) instead of 5-step DQLDQL · MuJoCo 9 tasksaverage normalized score: 87.9 -> 92.6 (+4.7)Improved
apply one-step DDIM sampler to pretrained DQL at inference (ablation)DQL · MuJoCo 9 tasksaverage normalized score: 87.9 -> 11.6 (-76.3)Hurt
use FBRAC flow policy with single inference step (ablation)DQL · MuJoCo 9 tasksaverage normalized score: 87.9 -> 67.1 (-20.8)Hurt
distill one-step policy from multi-step flow (FQL) (ablation)DQL · MuJoCo 9 tasksaverage normalized score: 87.9 -> 79.2 (-8.7)Hurt
flow ratio 0.5 instead of 1 (pure flow matching) (ablation)OFQL · HalfCheetah-Medium-ExpertD4RL score: 38.3 -> 95.2Improved
flow ratio 0.5 instead of 0 (ablation)OFQL · HalfCheetah-Medium-ReplayD4RL score: 10.5 -> 51.2Improved
flow ratio 0.5 instead of 0 (ablation)OFQL · HalfCheetah-MediumD4RL score: 63.2 -> 63.8Improved
flow ratio 0.5 instead of 0.25 (ablation)OFQL · HalfCheetah-MediumD4RL score: 63.76 -> 63.8No clear effect
replace DQL with OFQLDQL · AntMaze averageD4RL normalized score: 64.6 -> 84.6Improved
replace DQL with OFQLDQL · Kitchen averageD4RL normalized score: 61.6 -> 67.0Improved
replace DQL with OFQLDQL · MuJoCo averageD4RL normalized score: 87.9 to 92.5Improved
use OFQL one-step training instead of 5-step DQLDQL · MuJoCo training time over 1M stepstraining hours: 11.7 hours at 5 steps -> 6.3 hoursImproved

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