Junpeng Jiang

reinforcement learning (1) imitation learning (1) variational inference (1) autonomous driving (1) policy learning (1) world model (1) adversarial imitation learning (1) generative adversarial imitation learning (1) generative adversarial (1) closed-loop simulation (1) variational discriminator bottleneck (1) image difference (1) third-person perspective (1) end-to-end planning (1) autonomous driving simulation (1) third-person learning (1) 4d world representation (1) visual scene synthesis (1) diffusion-based video generation (1)