Jonathan P. How

reinforcement learning (2) multi-agent reinforcement learning (2) multi-task learning (1) object detection (1) hierarchical reinforcement learning (1) adversarial robustness (1) point cloud registration (1) linear function approximation (1) clustering algorithm (1) knowledge transfer (1) bayesian nonparametrics (1) branch and bound (1) value function (1) policy iteration (1) 3d reconstruction (1) partial observability (1) temporal abstraction (1) bayesian nonparametric (1) representation learning (1) deep reinforcement learning (1)