Breaking the sample size barrier in model-based reinforcement learning with a generative model G Li, Y Wei, Y Chi, Y Gu, Y Chen Advances in neural information processing systems 33, 12861-12872, 2020 | 133 | 2020 |
Sample complexity of asynchronous Q-learning: Sharper analysis and variance reduction G Li, Y Wei, Y Chi, Y Gu, Y Chen IEEE Transactions on Information Theory 68 (1), 448-473, 2021 | 113 | 2021 |
Nonconvex low-rank tensor completion from noisy data C Cai, G Li, HV Poor, Y Chen Advances in neural information processing systems 32, 2019 | 111 | 2019 |
Pessimistic q-learning for offline reinforcement learning: Towards optimal sample complexity L Shi, G Li, Y Wei, Y Chen, Y Chi International conference on machine learning, 19967-20025, 2022 | 96 | 2022 |
Phase transitions of spectral initialization for high-dimensional non-convex estimation YM Lu, G Li Information and Inference: A Journal of the IMA 9 (3), 507-541, 2020 | 93 | 2020 |
Settling the sample complexity of model-based offline reinforcement learning G Li, L Shi, Y Chen, Y Chi, Y Wei The Annals of Statistics 52 (1), 233-260, 2024 | 80 | 2024 |
Is Q-learning minimax optimal? a tight sample complexity analysis G Li, C Cai, Y Chen, Y Wei, Y Chi Operations Research, 2023 | 80 | 2023 |
Subspace estimation from unbalanced and incomplete data matrices: ℓ2,∞ statistical guarantees C Cai, G Li, Y Chi, HV Poor, Y Chen The Annals of Statistics 49 (2), 944-967, 2021 | 72 | 2021 |
Softmax policy gradient methods can take exponential time to converge G Li, Y Wei, Y Chi, Y Gu, Y Chen Conference on Learning Theory, 3107-3110, 2021 | 56* | 2021 |
Breaking the sample complexity barrier to regret-optimal model-free reinforcement learning G Li, L Shi, Y Chen, Y Gu, Y Chi Advances in Neural Information Processing Systems 34, 17762-17776, 2021 | 49 | 2021 |
The efficacy of pessimism in asynchronous Q-learning Y Yan, G Li, Y Chen, J Fan IEEE Transactions on Information Theory, 2023 | 48 | 2023 |
Restricted isometry property of gaussian random projection for finite set of subspaces G Li, Y Gu IEEE Transactions on Signal Processing 66 (7), 1705-1720, 2017 | 38 | 2017 |
Active orthogonal matching pursuit for sparse subspace clustering Y Chen, G Li, Y Gu IEEE Signal Processing Letters 25 (2), 164-168, 2017 | 36 | 2017 |
Towards faster non-asymptotic convergence for diffusion-based generative models G Li, Y Wei, Y Chen, Y Chi arXiv preprint arXiv:2306.09251, 2023 | 35 | 2023 |
Sample-efficient reinforcement learning is feasible for linearly realizable MDPs with limited revisiting G Li, Y Chen, Y Chi, Y Gu, Y Wei Advances in Neural Information Processing Systems 34, 16671-16685, 2021 | 30 | 2021 |
A non-asymptotic framework for approximate message passing in spiked models G Li, Y Wei arXiv preprint arXiv:2208.03313, 2022 | 27 | 2022 |
Phase retrieval using iterative projections: Dynamics in the large systems limit G Li, Y Gu, YM Lu 2015 53rd Annual Allerton Conference on Communication, Control, and …, 2015 | 27 | 2015 |
The curious price of distributional robustness in reinforcement learning with a generative model L Shi, G Li, Y Wei, Y Chen, M Geist, Y Chi Advances in Neural Information Processing Systems 36, 2024 | 26 | 2024 |
Minimax-optimal multi-agent RL in Markov games with a generative model G Li, Y Chi, Y Wei, Y Chen Advances in Neural Information Processing Systems 35, 15353-15367, 2022 | 25* | 2022 |
Model-based reinforcement learning is minimax-optimal for offline zero-sum markov games Y Yan, G Li, Y Chen, J Fan arXiv preprint arXiv:2206.04044, 2022 | 25 | 2022 |