Or Avner

motion planning (1) imitation learning (1) policy gradient (1) supervised learning (1) policy learning (1) behavior cloning (1) dynamic programming (1) continuous control (1) goal-conditioned reinforcement learning (1) trajectory planning (1) trajectory embedding (1) inverse function learning (1) control learning (1) goal-based reinforcement learning (1) sub-goal tree (1) iterative inversion (1)