Peixi Peng

visual reinforcement learning (6) representation learning (5) autonomous driving (4) reinforcement learning (4) policy learning (3) vision-based reinforcement learning (2) imitation learning (2) frequency domain (2) person re-identification (2) unsupervised learning (2) class-incremental learning (2) sample efficiency (2) deep reinforcement learning (2) transfer learning (2) domain adaptation (2) knowledge distillation (2) multi-agent cooperation (2) data augmentation (2) variational inference (1) domain generalization (1)