works on
demonstration retrieval 1generative models 1offline reinforcement learning 1policy generalization 1retrieval-based planning 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

RAD: Retrieval High-quality Demonstrations to Enhance Decision-making

Lu Guo, Yixiang Shan, Zhengbang Zhu +5

The paper proposes RAD, a method that improves offline reinforcement learning by retrieving high-return states from the dataset and generating sub-trajectories toward these targets…