Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation



Pihe Hu , Yu Chen , Longbo Huang

* Accepted by ICML 2022 

   Access Paper or Ask Questions

Provable Generalization of Overparameterized Meta-learning Trained with SGD



Yu Huang , Yingbin Liang , Longbo Huang

* 45 pages, 3 figures 

   Access Paper or Ask Questions

Risk-Sensitive Reinforcement Learning: Iterated CVaR and the Worst Path



Yihan Du , Siwei Wang , Longbo Huang


   Access Paper or Ask Questions

RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch



Yiqin Tan , Pihe Hu , Ling Pan , Longbo Huang


   Access Paper or Ask Questions

Network Topology Optimization via Deep Reinforcement Learning



Zhuoran Li , Xing Wang , Ling Pan , Lin Zhu , Zhendong Wang , Junlan Feng , Chao Deng , Longbo Huang


   Access Paper or Ask Questions

Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)



Yu Huang , Junyang Lin , Chang Zhou , Hongxia Yang , Longbo Huang

* 41 pages, 2 figures 

   Access Paper or Ask Questions

Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits



Jiatai Huang , Yan Dai , Longbo Huang


   Access Paper or Ask Questions

Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification



Ling Pan , Longbo Huang , Tengyu Ma , Huazhe Xu


   Access Paper or Ask Questions

Simultaneously Achieving Sublinear Regret and Constraint Violations for Online Convex Optimization with Time-varying Constraints



Qingsong Liu , Wenfei Wu , Longbo Huang , Zhixuan Fang

* Proceedings of the 39th International Symposium on Computer Performance, Modeling, Measurements and Evaluation (Performance), 2021 
* 31 pages, it has been accepted at Performance 2021 

   Access Paper or Ask Questions

Collaborative Pure Exploration in Kernel Bandit



Yihan Du , Wei Chen , Yuko Yuroki , Longbo Huang


   Access Paper or Ask Questions

1
2
3
4
>>