Zhenxian Liu

deep reinforcement learning (1) reinforcement learning (1) ensemble learning (1) knowledge distillation (1) policy learning (1) visual reinforcement learning (1) continuous control (1) model-based reinforcement learning (1) continuous action space (1) vision language model (1) world model (1) uncertainty estimation (1) policy network (1) image-based control (1) visual control (1) residual action (1)