Ruosong Wang
Carnegie Mellon University
H-index: 24
North America-United States
Top articles of Ruosong Wang
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
Horizon-free and variance-dependent reinforcement learning for latent Markov decision processes | Runlong Zhou Ruosong Wang Simon Shaolei Du | 2023/7/3 | |
Provably efficient reinforcement learning via surprise bound | Hanlin Zhu Ruosong Wang Jason Lee | 2023/4/11 | |
Settling the horizon-dependence of sample complexity in reinforcement learning | Yuanzhi Li Ruosong Wang Lin F Yang | 2022/2/7 | |
Tackling Challenges in Modern Reinforcement Learning: Long Planning Horizons and Large State Spaces | Ruosong Wang | 2022/2 | |
Tight Bounds for ℓ1 Oblivious Subspace Embeddings | ACM Transactions on Algorithms (TALG) | Ruosong Wang David P Woodruff | 2022/1/24 |
Horizon-free reinforcement learning for latent markov decision processes | Runlong Zhou Ruosong Wang Simon Shaolei Du | 2022/9/29 | |
Variance-aware sparse linear bandits | arXiv preprint arXiv:2205.13450 | Yan Dai Ruosong Wang Simon S Du | 2022/5/26 |
Online sub-sampling for reinforcement learning with general function approximation | arXiv preprint arXiv:2106.07203 | Dingwen Kong Ruslan Salakhutdinov Ruosong Wang Lin F Yang | 2021/6/14 |
Tight bounds for the subspace sketch problem with applications | SIAM Journal on Computing | Yi Li Ruosong Wang David P Woodruff | 2021 |
An exponential lower bound for linearly realizable mdp with constant suboptimality gap | Advances in Neural Information Processing Systems | Yuanhao Wang Ruosong Wang Sham Kakade | 2021/12/6 |
Bilinear classes: A structural framework for provable generalization in rl | Simon Du Sham Kakade Jason Lee Shachar Lovett Gaurav Mahajan | 2021/7/1 | |
Instabilities of offline rl with pre-trained neural representation | Ruosong Wang Yifan Wu Ruslan Salakhutdinov Sham Kakade | 2021/7/1 | |
On reward-free reinforcement learning with linear function approximation | Advances in neural information processing systems | Ruosong Wang Simon S Du Lin Yang Russ R Salakhutdinov | 2020 |
Provably efficient exploration for RL with unsupervised learning | arXiv preprint arXiv:2003.06898 | Fei Feng Ruosong Wang Wotao Yin Simon S Du Lin F Yang | 2020/3 |
Preference-based reinforcement learning with finite-time guarantees | arXiv preprint arXiv:2006.08910 | Yichong Xu Ruosong Wang Lin F Yang Aarti Singh Artur Dubrawski | 2020/6/16 |
Agnostic -learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity | Advances in Neural Information Processing Systems | Simon S Du Jason D Lee Gaurav Mahajan Ruosong Wang | 2020 |
The communication complexity of optimization | Santosh S Vempala Ruosong Wang David P Woodruff | 2020 | |
Reinforcement learning with general value function approximation: Provably efficient approach via bounded eluder dimension | Advances in Neural Information Processing Systems | Ruosong Wang Russ R Salakhutdinov Lin Yang | 2020 |
Nearly linear row sampling algorithm for quantile regression | Yi Li Ruosong Wang Lin Yang Hanrui Zhang | 2020/11/21 | |
Is long horizon rl more difficult than short horizon rl? | Advances in Neural Information Processing Systems | Ruosong Wang Simon S Du Lin Yang Sham Kakade | 2020 |