Victor Bapst

deep reinforcement learning (2) transfer learning (1) scene understanding (1) knowledge distillation (1) model-based reinforcement learning (1) monte-carlo tree search (1) robust learning (1) monte carlo tree search (1) structured representation (1) shared policy (1) multitask reinforcement learning (1) policy distillation (1) physical reasoning (1) object-centric action (1) physical construction (1)