Simon Schmitt

reinforcement learning (5) off-policy learning (2) model-based reinforcement learning (2) policy optimization (2) epistemic uncertainty (2) policy iteration (2) continuous control (2) policy learning (1) online learning (1) catastrophic forgetting (1) uncertainty quantification (1) model-based learning (1) function approximation (1) deep learning (1) multi-task learning (1) value function (1) importance sampling (1) policy gradient (1) value iteration (1) posterior distribution (1)