Pratap Tokekar

robot manipulation (2) multi-agent reinforcement learning (1) reinforcement learning (1) sample efficiency (1) adversarial robustness (1) imitation learning (1) path planning (1) policy gradient (1) geometric deep learning (1) visual reinforcement learning (1) behavior cloning (1) model-based reinforcement learning (1) posterior estimation (1) continuous action space (1) score function (1) approximation algorithm (1) inductive bia (1) equivariant graph neural network (1) reward shaping (1) trajectory generation (1)