Push-T

The 'Push-T' dataset/benchmark contains manipulation tasks designed to evaluate the performance of reinforcement learning algorithms in pushing objects, specifically assessing their effectiveness in learning and executing manipulation strategies.

Papers using Push-T (7)

Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy2026Global Contact-rich Planning With Sparsity-rich Semidefinite Relaxations2025 · 2 citesDinov3-diffusion Policy: Self-supervised Large Visual Model For Visuomotor Diffusion Policy Learning2025DINOv3-Diffusion Policy: Self-Supervised Large Visual Model for Visuomotor Diffusion Policy Learning2025Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition2025DDP-WM: Disentangled Dynamics Prediction for Efficient World Models2026Coupled Local and Global World Models for Efficient First Order RL2026