AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Enhancing Diffusion Policies with Distribution-Matching Generator in Offline Reinforcement Learning

Xuemin Hu, Shen Li, Yingfen Xu, Bo Tang, Long Chen

AAAI 2026 · Reinforcement learning › Offline RL · approach: Offline RL sample complexity theory · 0 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
use diffusion policy instead of Gaussian (VAE) policy (ablation)DMGDP · D4RL Gym-MuJoCo meannormalized score: 86.06 -> 94.28Improved
use diffusion policy instead of Gaussian policy (ablation)DMGDP · D4RL Hopper-mediumnormalized score: 60.2 -> 101.3Improved
add discriminator-based policy confidence (ablation)DMGDP · D4RL 10-task meannormalized score: 88.83 -> 93.01Improved
add policy confidence (ablation)DMGDP · D4RL Antmaze-medium-playnormalized score: 79 -> 85.3Improved
add policy confidence (ablation)DMGDP · D4RL Walker2d-mediumnormalized score: 89.2 -> 88.7No clear effect
vary lambda from 0.5 to 8 (ablation)DMGDP · D4RL Antmaze-mediumsuccess rateNo clear effect
use DMGDP instead of D-DICEDMGDP · D4RL Antmaze-large-playnormalized score: 68.6 -> 62.7Hurt
use DMGDP instead of DQLDMGDP · D4RL all-tasks meannormalized score: 80.6 -> 89.54Improved

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