Zechu Li

Robotics (1)

reinforcement learning (3) sample efficiency (1) imitation learning (1) policy gradient (1) multimodal learning (1) continuous control (1) off-policy learning (1) off-policy reinforcement learning (1) robot manipulation (1) intrinsic motivation (1) diffusion model (1) actor-critic algorithm (1) diffusion policy (1) multimodal behavior (1) mode-specific learning (1) sparse reward (1) value function learning (1) digital twin (1) parallel q-learning (1) massively parallel simulation (1)