Miao Lu
Recent News(Mar. 2024) I am presenting our work ‘‘Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage’’ at CISS 2024, see you at Princeton! (Jan. 2024) Our paper (Benign Oscillation) accepted to International Conference on Learning Representations (ICLR) 2024! (Oct. 2023) A new work released: ‘‘Benign Oscillation’’ for explaining generalization of large learning rate neural network training. |