Jesse Farebrother

dimensionality reduction (1) reinforcement learning (1) stochastic gradient descent (1) temporal difference learning (1) matrix factorization (1) policy gradient (1) distributional reinforcement learning (1) dynamic programming (1) continuous control (1) principal subspace (1) return distribution (1) soft actor-critic (1) deep q-network (1) multivariate reward (1) neural network (1)