Manan Tomar

representation learning (3) reinforcement learning (2) multi-task learning (1) offline reinforcement learning (1) visual observation (1) robotic manipulation (1) variational inference (1) information bottleneck (1) curriculum learning (1) self-supervised learning (1) dynamic programming (1) value iteration (1) policy iteration (1) skill discovery (1) temporal abstraction (1) robot manipulation (1) model-free reinforcement learning (1) sparse reward (1) successor representation (1) robust control (1)