 Online Learning of Decision Trees with Thompson SamplingInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2024 |
 On The Convergence Of Policy Iteration-Based Reinforcement Learning With
Monte Carlo Policy EvaluationInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 |
 Slowly Changing Adversarial Bandit Algorithms are Efficient for
Discounted MDPsInternational Conference on Algorithmic Learning Theory (ALT), 2022 |
