Tim Pearce

reinforcement learning (3) kernel methods (2) ensemble method (2) policy optimization (2) uncertainty quantification (2) gaussian process (2) bayesian neural network (2) prior knowledge (1) imitation learning (1) sample efficiency (1) policy learning (1) model uncertainty (1) probabilistic inference (1) approximate inference (1) survival analysis (1) bayesian inference (1) model-based reinforcement learning (1) reward function (1) kernel combination (1) quantile regression (1)