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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Minimax-Optimal Multi-Agent RL in Zero-Sum Markov Games With a Generative Model


Aug 22, 2022
Gen Li, Yuejie Chi, Yuting Wei, Yuxin Chen


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Non-Asymptotic Framework for Approximate Message Passing in Spiked Models


Aug 05, 2022
Gen Li, Yuting Wei


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Mitigating multiple descents: A model-agnostic framework for risk monotonization


May 25, 2022
Pratik Patil, Arun Kumar Kuchibhotla, Yuting Wei, Alessandro Rinaldo

* 110 pages, 15 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Settling the Sample Complexity of Model-Based Offline Reinforcement Learning


Apr 11, 2022
Gen Li, Laixi Shi, Yuxin Chen, Yuejie Chi, Yuting Wei


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity


Feb 28, 2022
Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen, Yuejie Chi


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Minimum $\ell_{1}$-norm interpolators: Precise asymptotics and multiple descent


Oct 18, 2021
Yue Li, Yuting Wei


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization


May 31, 2021
Shicong Cen, Yuting Wei, Yuejie Chi


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting


May 17, 2021
Gen Li, Yuxin Chen, Yuejie Chi, Yuantao Gu, Yuting Wei


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis


Mar 16, 2021
Gen Li, Changxiao Cai, Yuxin Chen, Yuantao Gu, Yuting Wei, Yuejie Chi

* v2 added a matching lower bound, and removed the finite-horizon setting for brevity 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Softmax Policy Gradient Methods Can Take Exponential Time to Converge


Feb 22, 2021
Gen Li, Yuting Wei, Yuejie Chi, Yuantao Gu, Yuxin Chen


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
>>