Daniil Tiapkin

markov decision process (4) bayesian inference (2) posterior sampling (2) stochastic optimization (2) regret bound (2) probabilistic modeling (1) non-convex optimization (1) temporal difference learning (1) optimal transport (1) bayesian reinforcement learning (1) primal-dual optimization (1) sample complexity (1) distributed learning (1) policy learning (1) dirichlet process (1) regret minimization (1) computational complexity (1) policy optimization (1) gradient descent (1) policy evaluation (1)