Jaron Sanders

reinforcement learning (1) stochastic gradient descent (1) policy gradient (1) sample complexity (1) universal approximation (1) markov decision process (1) exponential family (1) stationary distribution (1) regret bound (1) convergence rate (1) stationary point (1) stochastic gradient ascent (1) feed-forward network (1) average-reward reinforcement learning (1) neural network (1) score-aware gradient estimator (1) local lyapunov stability (1) random filter (1)