Kevin Zakka

dexterous manipulation (2) sim-to-real transfer (1) self-supervised learning (1) inverse reinforcement learning (1) robot learning (1) high-dimensional control (1) policy training (1) physics simulation (1) robotic hand (1) quadruped robot (1) cross-embodiment imitation (1) visual reward function (1) temporal cycle-consistency (1) deep reinforcement learning (1) deep visual embedding (1)