6 papers
Learning Geometrically-Grounded 3D Visual Representations for View-Generalizable Robotic Manipulation
Di Zhang, Weicheng Duan, Dasen Gu +5
Real-world robotic manipulation demands visuomotor policies capable of robust spatial scene understanding and strong generalization across diverse camera viewpoints. While recent a…
ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory Rollouts
Hang Yu, Di Zhang, Qiwei Du +5
Offline reinforcement learning (RL) enables agents to learn optimal policies from pre-collected datasets. However, datasets containing suboptimal and fragmented trajectories presen…
KineDex: Learning Tactile-Informed Visuomotor Policies via Kinesthetic Teaching for Dexterous Manipulation
Di Zhang, Chengbo Yuan, Chuan Wen +3
Collecting demonstrations enriched with fine-grained tactile information is critical for dexterous manipulation, particularly in contact-rich tasks that require precise force contr…
Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning
Hai Zhang, Boyuan Zheng, Tianying Ji +4
Offline meta reinforcement learning (OMRL) has emerged as a promising approach for interaction avoidance and strong generalization performance by leveraging pre-collected data and…
Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning
Lanqing Li, Hai Zhang, Xinyu Zhang +4
As a marriage between offline RL and meta-RL, the advent of offline meta-reinforcement learning (OMRL) has shown great promise in enabling RL agents to multi-task and quickly adapt…
Focus On What Matters: Separated Models For Visual-Based RL Generalization
Di Zhang, Bowen Lv, Hai Zhang +7
A primary challenge for visual-based Reinforcement Learning (RL) is to generalize effectively across unseen environments. Although previous studies have explored different auxiliar…