Ruohan Wang

few-shot learning (2) imitation learning (1) transfer learning (1) structured prediction (1) reward function estimation (1) training stability (1) task adaptation (1) continuous domain (1) policy distribution (1) non-parametric method (1) expert policy support (1) global label (1) conditional meta-learning (1) task-adaptive meta-learning (1) model-agnostic learning (1) feature pretraining (1)