Yaru Niu

reinforcement learning (2) multi-task learning (1) autonomous driving (1) markov decision process (1) continuous control (1) distributional robustness (1) decision tree (1) hierarchical latent variable (1) interpretable policy (1) multi-task reinforcement learning (1) ambiguity set (1) group distributionally robust (1) belief uncertainty (1) quadrupedal manipulation (1) cross-embodiment imitation learning (1) human pretraining (1) modularized architecture (1) teleoperation pipeline (1) locoman robot (1)