 Reinforcement Learning with History-Dependent Dynamic ContextsInternational Conference on Machine Learning (ICML), 2023 |
 Cooperative Online Learning in Stochastic and Adversarial MDPsInternational Conference on Machine Learning (ICML), 2022 |
 On the Theory of Reinforcement Learning with Once-per-Episode FeedbackNeural Information Processing Systems (NeurIPS), 2021 |
 Minimax Regret for Stochastic Shortest PathNeural Information Processing Systems (NeurIPS), 2021 |
