Garrett Thomas

convolutional neural network (2) value iteration (2) differentiable planning (2) model-based reinforcement learning (2) offline reinforcement learning (1) policy optimization (1) robotic manipulation (1) domain generalization (1) path planning (1) transfer learning (1) deep learning (1) model uncertainty (1) continuous control (1) worst-case performance (1) safe reinforcement learning (1) distributional shift (1) model-based approach (1) trajectory planning (1) value iteration network (1) planning module (1)