Wilko Schwarting

continuous control (4) deep reinforcement learning (2) neural network (2) upper confidence bound (2) uncertainty quantification (2) model-based reinforcement learning (2) game theory (1) sim-to-real transfer (1) reinforcement learning (1) point cloud registration (1) epistemic uncertainty (1) motion estimation (1) autonomous driving (1) model predictive control (1) imitation learning (1) value function (1) hyperparameter optimization (1) optimal control (1) constrained optimization (1) policy gradient (1)