Sahand Rezaei-Shoshtari

policy gradient (2) continuous control (2) tactile sensing (2) reinforcement learning (2) multimodal learning (1) multi-modal learning (1) value function approximation (1) mdp homomorphisms (1) variational autoencoder (1) meta reinforcement learning (1) zero-shot transfer (1) contextual reinforcement learning (1) motion prediction (1) intuitive physics (1) contact interaction (1) deep learning architecture (1) visuotactile sensor (1) multimodal variational autoencoder (1) physics prediction (1) contextual rl (1)