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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Haipeng Luo

Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses


Jul 18, 2021
Haipeng Luo, Chen-Yu Wei, Chung-Wei Lee


  Access Paper or Ask Questions

Last-iterate Convergence in Extensive-Form Games


Jun 27, 2021
Chung-Wei Lee, Christian Kroer, Haipeng Luo


  Access Paper or Ask Questions

Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path


Jun 15, 2021
Liyu Chen, Mehdi Jafarnia-Jahromi, Rahul Jain, Haipeng Luo


  Access Paper or Ask Questions

Online Learning for Stochastic Shortest Path Model via Posterior Sampling


Jun 09, 2021
Mehdi Jafarnia-Jahromi, Liyu Chen, Rahul Jain, Haipeng Luo


  Access Paper or Ask Questions

The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition


Jun 08, 2021
Tiancheng Jin, Longbo Huang, Haipeng Luo


  Access Paper or Ask Questions

Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously


Feb 12, 2021
Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei, Mengxiao Zhang, Xiaojin Zhang


  Access Paper or Ask Questions

Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach


Feb 10, 2021
Chen-Yu Wei, Haipeng Luo


  Access Paper or Ask Questions

Finding the Stochastic Shortest Path with Low Regret: The Adversarial Cost and Unknown Transition Case


Feb 10, 2021
Liyu Chen, Haipeng Luo


  Access Paper or Ask Questions

Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games


Feb 08, 2021
Chen-Yu Wei, Chung-Wei Lee, Mengxiao Zhang, Haipeng Luo


  Access Paper or Ask Questions

Impossible Tuning Made Possible: A New Expert Algorithm and Its Applications


Feb 01, 2021
Liyu Chen, Haipeng Luo, Chen-Yu Wei


  Access Paper or Ask Questions

Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition


Dec 07, 2020
Liyu Chen, Haipeng Luo, Chen-Yu Wei


  Access Paper or Ask Questions

Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation


Jul 23, 2020
Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo, Rahul Jain


  Access Paper or Ask Questions

Comparator-adaptive Convex Bandits


Jul 16, 2020
Dirk van der Hoeven, Ashok Cutkosky, Haipeng Luo

* 15 pages 

  Access Paper or Ask Questions

Active Online Domain Adaptation


Jun 25, 2020
Yining Chen, Haipeng Luo, Tengyu Ma, Chicheng Zhang


  Access Paper or Ask Questions

Open Problem: Model Selection for Contextual Bandits


Jun 19, 2020
Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo

* COLT 2020 open problem 

  Access Paper or Ask Questions

Linear Last-iterate Convergence for Matrix Games and Stochastic Games


Jun 16, 2020
Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei, Mengxiao Zhang


  Access Paper or Ask Questions

Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs


Jun 14, 2020
Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei, Mengxiao Zhang


  Access Paper or Ask Questions

Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition


Jun 10, 2020
Tiancheng Jin, Haipeng Luo


  Access Paper or Ask Questions

A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret


Jun 08, 2020
Mehdi Jafarnia-Jahromi, Chen-Yu Wei, Rahul Jain, Haipeng Luo


  Access Paper or Ask Questions

Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret Bounds


Mar 07, 2020
Ehsan Emamjomeh-Zadeh, Chen-Yu Wei, Haipeng Luo, David Kempe


  Access Paper or Ask Questions

Taking a hint: How to leverage loss predictors in contextual bandits?


Mar 04, 2020
Chen-Yu Wei, Haipeng Luo, Alekh Agarwal


  Access Paper or Ask Questions

A Closer Look at Small-loss Bounds for Bandits with Graph Feedback


Feb 02, 2020
Chung-Wei Lee, Haipeng Luo, Mengxiao Zhang


  Access Paper or Ask Questions

Learning Adversarial MDPs with Bandit Feedback and Unknown Transition


Jan 07, 2020
Chi Jin, Tiancheng Jin, Haipeng Luo, Suvrit Sra, Tiancheng Yu

* Improved the algorithm with a tighter confidence set 

  Access Paper or Ask Questions

Fair Contextual Multi-Armed Bandits: Theory and Experiments


Dec 13, 2019
Yifang Chen, Alex Cuellar, Haipeng Luo, Jignesh Modi, Heramb Nemlekar, Stefanos Nikolaidis

* 9 pages, 9 figures 

  Access Paper or Ask Questions

Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes


Oct 15, 2019
Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo, Hiteshi Sharma, Rahul Jain


  Access Paper or Ask Questions

Model selection for contextual bandits


Jun 03, 2019
Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo


  Access Paper or Ask Questions

Equipping Experts/Bandits with Long-term Memory


May 30, 2019
Kai Zheng, Haipeng Luo, Ilias Diakonikolas, Liwei Wang

* 24 pages 

  Access Paper or Ask Questions