David Meger

reinforcement learning (4) continuous control (4) value function (3) 3d reconstruction (3) tactile sensing (3) policy gradient (3) deep reinforcement learning (2) 3d object reconstruction (2) value function approximation (2) mesh reconstruction (2) multi-modal learning (2) transfer learning (1) robotic manipulation (1) ensemble learning (1) imitation learning (1) continual learning (1) offline reinforcement learning (1) epistemic uncertainty (1) state abstraction (1) uncertainty quantification (1)