AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Instructed Diffuser With Temporal Condition Guidance for Offline Reinforcement Learning

Jifeng Hu, Yanchao Sun, Sili Huang, Siyuan Guo, Hechang Chen, Li Shen, Lichao Sun, Yi Chang, Dacheng Tao

TPAMI 2026 · Reinforcement learning › Offline RL · approach: Diffusion models for offline decision making · 25 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 historical condition (vs FAR-RTG-TS) (ablation)TCD · Gym-MuJoCo successful comparisonmean score: 84.98 -> 85.67Improved
add immediate condition to HC-RTG-TS (ablation)TCD · Gym-MuJoCo successful comparisonmean score: 85.31 -> 85.67Improved
add historical and immediate conditions to RTG-only (ablation)RTG-TS · Gym-MuJoCo successful comparisonmean score: 82.87 -> 85.67Improved
add historical and immediate conditions to RTG-only (ablation)RTG-TS · Gym-MuJoCo general comparisonmean score: 66.45 -> 77.65Improved
add historical condition (vs immediate only) (ablation)TCD · Gym-MuJoCo general comparisonmean score: 72.33 -> 77.65Improved
replace U-net with transformer backbone (TFD) (ablation)Diffuser · Gym-MuJoCo successful comparisonmean score: 85.67 -> 43.37Hurt
use distributional Q value as condition (DQD) (ablation)Diffuser · Gym-MuJoCo successful comparisonmean score: 85.67 -> 34.79Hurt
replace statistical reward with linear reward regression (RR-TCD) (ablation)TCD · Gym-MuJoCo successful comparisonmean score: 85.67 -> 79.81Hurt
replace statistical reward with reward quantile regression (RQR-TCD) (ablation)TCD · Gym-MuJoCo successful comparisonmean score: 85.67 -> 85.06No clear effect
add temporal conditions (TCD vs DD) (ablation)DD · Maze2Dmean score: 30.71 -> 37.10Improved
add temporal conditions (TCD vs DD) (ablation)DD · Maze2D dense umazenormalized score: 83.23 -> 29.77Hurt
add temporal conditions (TCD vs DD) (ablation)DD · Gym-MuJoCo random datasetsmean score: 53.32 -> 55.32Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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