Siddhant Haldar

imitation learning (4) behavior cloning (2) robot manipulation (2) optimal transport (1) self-supervised learning (1) visual representation (1) inverse reinforcement learning (1) visuo-motor control (1) inverse dynamics model (1) forward dynamics model (1) dynamics model (1) latent space prediction (1) trajectory matching (1) residual policy (1) visual skill (1) action chunking (1) transformer architecture (1) multi-task policy learning (1) few-shot learning (1) interactive learning (1)