Dian Wang

equivariant neural network (4) sample efficiency (3) imitation learning (2) robotic manipulation (2) policy learning (2) reinforcement learning (2) partial observability (2) spatial action space (2) sample-efficient learning (1) q learning (1) grasp learning (1) planar grasp detection (1) on-robot learning (1) fully observable policy (1) state expert (1) deep reinforcement learning (1) equivariant reinforcement learning (1) motion planning (1) robot learning (1) robot manipulation (1)