Shinji Ito

Submodular Function Minimization with Dueling Oracle

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback

Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning

Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems

Optimal Regret of Bandits under Differential Privacy