PPL
Abolfazl Hashemi
Papers (4)
Unified High-Probability Analysis of Stochastic Variance-Reduced EstimationBeyond Bounded Variance: Variance-Reduced Normalized Methods for Nonconvex Optimization under Blum-Gladyshev NoiseQuotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement LearningA Finite-Iteration Theory for Asynchronous Categorical Distributional Temporal-Difference Learning