Title |
|---|
 Robust Offline Reinforcement learning with Heavy-Tailed RewardsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 |
 Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed
RewardsNeural Information Processing Systems (NeurIPS), 2023 |
 Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function
Approximation: Minimax Optimal and Instance-Dependent Regret BoundsNeural Information Processing Systems (NeurIPS), 2023 |
 Implicitly normalized forecaster with clipping for linear and non-linear
heavy-tailed multi-armed banditsComputational Management Science (CMS), 2023 |
