Title |
|---|
 Near-Optimal Regret in Linear MDPs with Aggregate Bandit FeedbackInternational Conference on Machine Learning (ICML), 2024 |
 Imitation Learning in Discounted Linear MDPs without exploration
assumptionsInternational Conference on Machine Learning (ICML), 2024 |
 Refined Sample Complexity for Markov Games with Independent Linear
Function ApproximationAnnual Conference Computational Learning Theory (COLT), 2024 |
 Rethinking Model-based, Policy-based, and Value-based Reinforcement
Learning via the Lens of Representation ComplexityNeural Information Processing Systems (NeurIPS), 2023 |
 Towards Optimal Regret in Adversarial Linear MDPs with Bandit FeedbackInternational Conference on Learning Representations (ICLR), 2023 |
