Convergence of the deep BSDE method for coupled FBSDEs J Han, J Long Probability, Uncertainty and Quantitative Risk 5 (1), 5, 2020 | 183 | 2020 |
Learning high-dimensional McKean–Vlasov forward-backward stochastic differential equations with general distribution dependence J Han, R Hu, J Long SIAM Journal on Numerical Analysis 62 (1), 1-24, 2024 | 28 | 2024 |
Convergence of deep fictitious play for stochastic differential games J Han, R Hu, J Long arXiv preprint arXiv:2008.05519, 2020 | 26 | 2020 |
An Analysis of Reinforcement Learning in High Dimensions with Kernel and Neural Network Approximation J Long, J Han arXiv preprint arXiv:2104.07794, 2021 | 21 | 2021 |
Perturbational complexity by distribution mismatch: A systematic analysis of reinforcement learning in reproducing kernel hilbert space J Long, J Han arXiv preprint arXiv:2111.03469, 2021 | 11 | 2021 |
A class of dimensionality-free metrics for the convergence of empirical measures J Han, R Hu, J Long arXiv preprint arXiv:2104.12036 196, 2021 | 10 | 2021 |
Empowering optimal control with machine learning: A perspective from model predictive control E Weinan, J Han, J Long IFAC-PapersOnLine 55 (30), 121-126, 2022 | 8 | 2022 |
A spectral-based analysis of the separation between two-layer neural networks and linear methods L Wu, J Long Journal of Machine Learning Research 23 (119), 1-34, 2022 | 8 | 2022 |
A class of dimension-free metrics for the convergence of empirical measures J Han, R Hu, J Long Stochastic Processes and their Applications 164, 242-287, 2023 | 6 | 2023 |
A machine learning enhanced algorithm for the optimal landing problem Y Zang, J Long, X Zhang, W Hu, E Weinan, J Han Mathematical and Scientific Machine Learning, 319-334, 2022 | 6 | 2022 |
Reinforcement learning with function approximation: From linear to nonlinear J Long, J Han arXiv preprint arXiv:2302.09703, 2023 | 4 | 2023 |
Initial value problem enhanced sampling for closed-loop optimal control design with deep neural networks X Zhang, J Long, W Hu, J Han arXiv preprint arXiv:2209.04078, 2022 | 4 | 2022 |
Deep Picard Iteration for High-Dimensional Nonlinear PDEs J Han, W Hu, J Long, Y Zhao arXiv preprint arXiv:2409.08526, 2024 | 1 | 2024 |
Finite-Agent Stochastic Differential Games on Large Graphs: I. The Linear-Quadratic Case R Hu, J Long, H Zhou arXiv preprint arXiv:2406.09523, 2024 | 1 | 2024 |
High-Dimensional Reinforcement Learning and Optimal Control Problems J Long Princeton University, 2023 | 1 | 2023 |
Solving optimal control of rigid-body dynamics with collisions using the hybrid minimum principle W Hu, J Long, Y Zang, J Han arXiv preprint arXiv:2205.08622, 2022 | 1 | 2022 |
Linear approximability of two-layer neural networks: A comprehensive analysis based on spectral decay J Long, L Wu arXiv e-prints, arXiv: 2108.04964, 2021 | 1 | 2021 |
A Duality Analysis of Kernel Ridge Regression in the Noiseless Regime J Long, X Peng, L Wu arXiv preprint arXiv:2402.15718, 2024 | | 2024 |
Learning Free Terminal Time Optimal Closed-loop Control of Manipulators W Hu, Y Zhao, J Han, J Long arXiv preprint arXiv:2311.17749, 2023 | | 2023 |
The Learnability of Reproducing Kernel Hilbert Spaces H Chen, J Long, L Wu arXiv preprint arXiv:2306.02833, 2023 | | 2023 |