Alexander Khazatsky

robot manipulation (2) robotic manipulation (1) text classification (1) self-supervised learning (1) model-based reinforcement learning (1) off-policy learning (1) generalization ability (1) lower bound (1) policy training (1) goal-conditioned reinforcement learning (1) zero-shot detection (1) model accuracy (1) machine-generated text (1) log probability (1) large language model (1) probability curvature (1) objective mismatch (1) goal setting (1) raw image observation (1) demonstration datum (1)