Qiangxing Tian

reinforcement learning (2) representation learning (1) independent component analysis (1) unsupervised domain adaptation (1) robot learning (1) intrinsic motivation (1) latent variable (1) goal-conditioned policy (1) reward shaping (1) intrinsic reward (1) dynamics model (1) skill transfer (1) skill acquisition (1) robotic learning (1) latent-conditioned policy (1) deep reinforcement learning (1) multi-goal setting (1)