Sangwoo Shin

zero-shot adaptation (2) zero-shot learning (1) offline reinforcement learning (1) imitation learning (1) multi-modal learning (1) reward function (1) language model (1) skill learning (1) vision-language model (1) embodied agent (1) task planning (1) non-stationary environment (1) cross-domain adaptation (1) multi-modal model (1) large language model (1) one-shot imitation (1) skill-based learning (1) semantic skill (1) cross-domain policy (1) reward ensemble (1)