Che Wang

deep reinforcement learning (3) representation learning (2) sample efficiency (2) imitation learning (1) robotic manipulation (1) self-supervised learning (1) multi-modal learning (1) policy learning (1) value function (1) continuous control (1) state representation (1) batch reinforcement learning (1) entropy maximization (1) off-policy learning (1) visual representation learning (1) replay buffer (1) evolutionary search (1) offline rl (1) auxiliary loss (1) sparse datum (1)