Picture for Shenghua Wan

Shenghua Wan

SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets

Add code
Jun 13, 2024
Viaarxiv icon

DIDA: Denoised Imitation Learning based on Domain Adaptation

Add code
Apr 04, 2024
Figure 1 for DIDA: Denoised Imitation Learning based on Domain Adaptation
Figure 2 for DIDA: Denoised Imitation Learning based on Domain Adaptation
Figure 3 for DIDA: Denoised Imitation Learning based on Domain Adaptation
Figure 4 for DIDA: Denoised Imitation Learning based on Domain Adaptation
Viaarxiv icon

SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring

Add code
Apr 04, 2024
Viaarxiv icon

AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors

Add code
Mar 15, 2024
Viaarxiv icon

SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models

Add code
Jun 19, 2023
Viaarxiv icon