Xianyuan Zhan

offline reinforcement learning (10) policy optimization (3) sim-to-real transfer (2) model-based learning (2) imitation learning (2) offline imitation learning (2) dynamics model (2) policy learning (1) data augmentation (1) sample efficiency (1) domain adaptation (1) transfer learning (1) few-shot learning (1) visual grounding (1) robot learning (1) spatio-temporal modeling (1) instruction following (1) behavior cloning (1) value function (1) adversarial learning (1)