Miao Lu
Recent News(Apr. 2024) Check out our new paper ‘‘Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm’’! We uncover the fundamental hardness of distributionally robust RL through interactive data collection in general, accompanied by a near-optimal algorithm for a solvable case. (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. |