Archit Sharma

reinforcement learning (3) sample efficiency (2) policy training (2) autonomous learning (2) imitation learning (2) direct preference optimization (2) large language model (2) reinforcement learning from human feedback (2) confidence calibration (1) self-supervised learning (1) adversarial learning (1) preference optimization (1) curriculum learning (1) continual adaptation (1) model predictive control (1) variational inference (1) language model alignment (1) human-robot interaction (1) instruction following (1) robotic manipulation (1)