Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

E$^2$DT: Efficient and Effective Decision Transformer with Experience-Aware Sampling for Robotic Manipulation

About

In reinforcement learning (RL) for robotic manipulation, the Decision Transformer (DT) has emerged as an effective framework for addressing long-horizon tasks. However, DT's performance depends heavily on the coverage of collected experiences. Without an active exploration mechanism, standard DT relies on uniform replay, which leads to poor sample efficiency, limited exploration, and reduced overall effectiveness. At the same time, while excessive exploration can help avoid local optima, it often delays policy convergence and leads to degraded efficiency. To address these limitations, we propose E$^2$DT, a DT-guided k-Determinantal Point Process sampling framework that enables the model to actively shape its own experience selection. Our framework is experience-aware, allowing E$^2$DT to be both efficient, by prioritizing sampling quality, such as high-return, high-uncertainty, and underrepresented trajectories, and effective, by ensuring diversity across trajectory windows to preserve policy optimality. Specifically, DT's internal latent embeddings measure diversity across trajectory windows, while quality is quantified through a composite metric that integrates return-to-go (RTG) quantiles, predictive uncertainty, and stage coverage based on inverse frequency. These two dimensions are integrated into a novel quality-diversity joint kernel that prioritizes the most informative experiences, thereby enabling learning that is both efficient and effective. We evaluate E$^2$DT on challenging robotic manipulation benchmarks in both simulation and real-robot settings. Results show that it consistently outperforms prior methods. These findings demonstrate that coupling policy learning with experience-aware sampling provides a principled path toward robust long-horizon robotic learning.

Kaiyan Zhao, Borong Zhang, Yiming Wang, Xingyu Liu, Xuetao Li, Yuyang Chen, Xiaoguang Niu• 2026

Related benchmarks

TaskDatasetResultRank
Block-stackingRoboSuite online finetuning
Mean Success Rate79.8
7
Door OpeningRoboSuite online finetuning
Mean Success Rate65.2
7
High-Shelf PlacementElephant Robotics 280 Real-world (test)
Success Rate82.1
7
Nut AssemblyRoboSuite online finetuning
Mean Success Rate55.6
7
Pick-&-PlaceRoboSuite online finetuning
Mean Success Rate73.7
7
StackingElephant Robotics 280 Real-world (test)
Success Rate85.6
7
Target GraspingElephant Robotics 280 Real-world (test)
Success Rate83.4
7
Showing 7 of 7 rows

Other info

Follow for update