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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation


Apr 19, 2022
Jongmin Lee, Cosmin Paduraru, Daniel J. Mankowitz, Nicolas Heess, Doina Precup, Kee-Eung Kim, Arthur Guez

* 24 pages, 6 figures, Accepted at ICLR 2022 (spotlight) 

   Access Paper or Ask Questions

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

MuZero with Self-competition for Rate Control in VP9 Video Compression


Feb 14, 2022
Amol Mandhane, Anton Zhernov, Maribeth Rauh, Chenjie Gu, Miaosen Wang, Flora Xue, Wendy Shang, Derek Pang, Rene Claus, Ching-Han Chiang, Cheng Chen, Jingning Han, Angie Chen, Daniel J. Mankowitz, Jackson Broshear, Julian Schrittwieser, Thomas Hubert, Oriol Vinyals, Timothy Mann


   Access Paper or Ask Questions

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

Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification


Oct 20, 2020
Daniel J. Mankowitz, Dan A. Calian, Rae Jeong, Cosmin Paduraru, Nicolas Heess, Sumanth Dathathri, Martin Riedmiller, Timothy Mann


   Access Paper or Ask Questions

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

Balancing Constraints and Rewards with Meta-Gradient D4PG


Oct 13, 2020
Dan A. Calian, Daniel J. Mankowitz, Tom Zahavy, Zhongwen Xu, Junhyuk Oh, Nir Levine, Timothy Mann


   Access Paper or Ask Questions

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

An empirical investigation of the challenges of real-world reinforcement learning


Mar 24, 2020
Gabriel Dulac-Arnold, Nir Levine, Daniel J. Mankowitz, Jerry Li, Cosmin Paduraru, Sven Gowal, Todd Hester

* arXiv admin note: text overlap with arXiv:1904.12901 

   Access Paper or Ask Questions

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

Robust Reinforcement Learning for Continuous Control with Model Misspecification


Jun 18, 2019
Daniel J. Mankowitz, Nir Levine, Rae Jeong, Abbas Abdolmaleki, Jost Tobias Springenberg, Timothy Mann, Todd Hester, Martin Riedmiller


   Access Paper or Ask Questions

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

Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces


May 23, 2019
Chen Tessler, Tom Zahavy, Deborah Cohen, Daniel J. Mankowitz, Shie Mannor


   Access Paper or Ask Questions

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

Soft-Robust Actor-Critic Policy-Gradient


Oct 24, 2018
Esther Derman, Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor

* UAI 2018 

   Access Paper or Ask Questions

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

Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning


Sep 06, 2018
Tom Zahavy, Matan Haroush, Nadav Merlis, Daniel J. Mankowitz, Shie Mannor


   Access Paper or Ask Questions

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

Unicorn: Continual Learning with a Universal, Off-policy Agent


Jul 03, 2018
Daniel J. Mankowitz, Augustin Žídek, André Barreto, Dan Horgan, Matteo Hessel, John Quan, Junhyuk Oh, Hado van Hasselt, David Silver, Tom Schaul


   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
>>