Honguk Woo

offline reinforcement learning (4) imitation learning (3) policy adaptation (3) reinforcement learning (3) large language model (3) diffusion model (3) skill learning (3) embodied agent (3) skill decomposition (2) zero-shot learning (2) policy distillation (2) task decomposition (2) zero-shot adaptation (2) robotic manipulation (2) continual learning (2) task planning (2) vision-language model (2) non-stationary environment (2) knowledge distillation (1) structure learning (1)