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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Confident Approximate Policy Iteration for Efficient Local Planning in $q^π$-realizable MDPs


Oct 27, 2022
Gellért Weisz, András György, Tadashi Kozuno, Csaba Szepesvári

Add code


   Access Paper or Ask Questions

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

KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal


May 27, 2022
Tadashi Kozuno, Wenhao Yang, Nino Vieillard, Toshinori Kitamura, Yunhao Tang, Jincheng Mei, Pierre Ménard, Mohammad Gheshlaghi Azar, Michal Valko, Rémi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvári

Add code

* 29 pages, 6 figures 

   Access Paper or Ask Questions

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

No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL


May 18, 2022
Han Wang, Archit Sakhadeo, Adam White, James Bell, Vincent Liu, Xutong Zhao, Puer Liu, Tadashi Kozuno, Alona Fyshe, Martha White

Add code


   Access Paper or Ask Questions

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

Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences


Jul 17, 2021
Alan Chan, Hugo Silva, Sungsu Lim, Tadashi Kozuno, A. Rupam Mahmood, Martha White

Add code

* Submitted to JMLR 

   Access Paper or Ask Questions

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

Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation


Jun 24, 2021
Yunhao Tang, Tadashi Kozuno, Mark Rowland, Rémi Munos, Michal Valko

Add code


   Access Paper or Ask Questions

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

Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall


Jun 11, 2021
Tadashi Kozuno, Pierre Ménard, Rémi Munos, Michal Valko

Add code

* 20 pages 

   Access Paper or Ask Questions

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

Identifying Co-Adaptation of Algorithmic and Implementational Innovations in Deep Reinforcement Learning: A Taxonomy and Case Study of Inference-based Algorithms


Mar 31, 2021
Hiroki Furuta, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo, Shixiang Shane Gu

Add code

* The implementation is available at: https://github.com/frt03/inference-based-rl 

   Access Paper or Ask Questions

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

Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning


Mar 23, 2021
Hiroki Furuta, Tatsuya Matsushima, Tadashi Kozuno, Yutaka Matsuo, Sergey Levine, Ofir Nachum, Shixiang Shane Gu

Add code


   Access Paper or Ask Questions

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

Revisiting Peng's Q($λ$) for Modern Reinforcement Learning


Feb 27, 2021
Tadashi Kozuno, Yunhao Tang, Mark Rowland, Rémi Munos, Steven Kapturowski, Will Dabney, Michal Valko, David Abel

Add code

* 26 pages, 7 figures, 2 tables 

   Access Paper or Ask Questions

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

Leverage the Average: an Analysis of Regularization in RL


Apr 10, 2020
Nino Vieillard, Tadashi Kozuno, Bruno Scherrer, Olivier Pietquin, Rémi Munos, Matthieu Geist

Add code


   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
>>