Jinxin Liu

offline reinforcement learning (5) reinforcement learning (3) imitation learning (2) cross-domain learning (2) intrinsic reward (2) hardware design (2) few-shot learning (1) multi-task learning (1) deep reinforcement learning (1) transfer learning (1) independent component analysis (1) preference learning (1) data augmentation (1) in-context learning (1) paraphrase generation (1) policy optimization (1) unsupervised domain adaptation (1) test-time adaptation (1) semantic parsing (1) representation learning (1)