AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

D²PPO: Diffusion Policy Policy Optimization with Dispersive Loss

Guowei Zou, Weibing Li, Hejun Wu, Yukun Qian, Yuhang Wang, Haitao Wang

AAAI 2026 · Reinforcement learning › Visual and representation RL · approach: Skill learning and diffusion policies · 4 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 dispersive loss regularization during diffusion policy pre-trainingDPPO · RoboMimic Lift to Transport (pre-training)success rate: +3.4% (Lift) to +36.2% (Transport); average 22.7%Improved
add dispersive pre-training before PPO fine-tuningDPPO · RoboMimic Transport (fine-tuned)success rate: 0.60 -> 0.87Improved
add dispersive pre-training before PPO fine-tuningDPPO · RoboMimic Square (fine-tuned)success rate: 0.83 -> 0.89Improved
add dispersive pre-training before PPO fine-tuningDPPO · RoboMimic Lift and Can (fine-tuned)success rate: 1.00 -> 1.00No clear effect
add dispersive pre-training before PPO fine-tuningDPPO · Real robot Transportsuccess rate: 45% -> 70%Improved
set dispersive loss coefficient lambda to 0.5 (ablation)D2PPO pre-training · RoboMimic Square (pre-training)success rate: 14.3% improvement over baselineImproved
set dispersive loss coefficient lambda to 0.3 (ablation)D2PPO pre-training · RoboMimic Square (pre-training)success rateHurt
set dispersive loss coefficient above 0.5 (ablation)D2PPO pre-training · RoboMimic Square (pre-training)success rateHurt
apply dispersive loss in early layers versus late layers (ablation)D2PPO · RoboMimic simple vs complex taskssuccess rateMixed
use L2 dispersive loss on middle layers versus other variants (ablation)D2PPO · RoboMimic pre-trainingstability and varianceImproved

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