Marin Vlastelica

deep reinforcement learning (1) variational inference (1) image retrieval (1) epistemic uncertainty (1) object detection (1) model-based learning (1) task-oriented dialogue (1) model predictive control (1) gradient descent (1) trajectory optimization (1) model-based reinforcement learning (1) zero-order optimization (1) amortized inference (1) latent variable (1) latent action (1) end-to-end training (1) rank-based metric (1) aleatoric uncertainty (1) amortized variational inference (1) policy architecture (1)