Kaiyan Zhao

deep reinforcement learning (3) exploration bonus (2) sentence embedding (2) reinforcement learning (2) sample efficiency (2) cross-lingual embedding (1) cross-lingual transfer (1) point cloud registration (1) transfer learning (1) policy optimization (1) contrastive learning (1) state abstraction (1) policy learning (1) word alignment (1) 3d vision (1) metric learning (1) gaussian process (1) continuous control (1) state representation (1) representation learning (1)