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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Upside-Down Reinforcement Learning Can Diverge in Stochastic Environments With Episodic Resets


May 13, 2022
Miroslav Štrupl, Francesco Faccio, Dylan R. Ashley, Jürgen Schmidhuber, Rupesh Kumar Srivastava

* presented at the 5th Multidisciplinary Conference on Reinforcement Learning and Decision Making; 5 pages in main text + 1 page of references + 3 pages of appendices, 1 figure in main text; source code available at https://github.com/struplm/UDRL-GCSL-counterexample.git 

   Access Paper or Ask Questions

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

Learning Relative Return Policies With Upside-Down Reinforcement Learning


Feb 23, 2022
Dylan R. Ashley, Kai Arulkumaran, J├╝rgen Schmidhuber, Rupesh Kumar Srivastava

* 5 pages in main text, 2 figures in main text 

   Access Paper or Ask Questions

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

Multimeasurement Generative Models


Dec 18, 2021
Saeed Saremi, Rupesh Kumar Srivastava


   Access Paper or Ask Questions

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

Reward-Weighted Regression Converges to a Global Optimum


Jul 19, 2021
Miroslav Štrupl, Francesco Faccio, Dylan R. Ashley, Rupesh Kumar Srivastava, Jürgen Schmidhuber

* 10 pages in main text + 2 pages of references + 4 pages of appendices, 2 figures in main text; source code available at https://github.com/dylanashley/reward-weighted-regression 

   Access Paper or Ask Questions

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

ClipUp: A Simple and Powerful Optimizer for Distribution-based Policy Evolution


Aug 05, 2020
Nihat Engin Toklu, Paweł Liskowski, Rupesh Kumar Srivastava

* 20 pages, 7 figures. Extended version of work appearing in PPSN 2020 

   Access Paper or Ask Questions

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

Training Agents using Upside-Down Reinforcement Learning


Dec 05, 2019
Rupesh Kumar Srivastava, Pranav Shyam, Filipe Mutz, Wojciech Ja┼Ťkowski, J├╝rgen Schmidhuber

* NNAISENSE Technical Report. 17 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

Artificial Intelligence for Prosthetics - challenge solutions


Feb 07, 2019
┼üukasz Kidzi┼äski, Carmichael Ong, Sharada Prasanna Mohanty, Jennifer Hicks, Sean F. Carroll, Bo Zhou, Hongsheng Zeng, Fan Wang, Rongzhong Lian, Hao Tian, Wojciech Ja┼Ťkowski, Garrett Andersen, Odd Rune Lykkeb├Ş, Nihat Engin Toklu, Pranav Shyam, Rupesh Kumar Srivastava, Sergey Kolesnikov, Oleksii Hrinchuk, Anton Pechenko, Mattias Ljungstr├Âm, Zhen Wang, Xu Hu, Zehong Hu, Minghui Qiu, Jun Huang, Aleksei Shpilman, Ivan Sosin, Oleg Svidchenko, Aleksandra Malysheva, Daniel Kudenko, Lance Rane, Aditya Bhatt, Zhengfei Wang, Penghui Qi, Zeyang Yu, Peng Peng, Quan Yuan, Wenxin Li, Yunsheng Tian, Ruihan Yang, Pingchuan Ma, Shauharda Khadka, Somdeb Majumdar, Zach Dwiel, Yinyin Liu, Evren Tumer, Jeremy Watson, Marcel Salath├ę, Sergey Levine, Scott Delp


   Access Paper or Ask Questions

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

ContextVP: Fully Context-Aware Video Prediction


Sep 09, 2018
Wonmin Byeon, Qin Wang, Rupesh Kumar Srivastava, Petros Koumoutsakos

* 19 pages. ECCV 2018 oral presentation. Project webpage is at https://wonmin-byeon.github.io/publication/2018-eccv 

   Access Paper or Ask Questions

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

LSTM: A Search Space Odyssey


Oct 04, 2017
Klaus Greff, Rupesh Kumar Srivastava, Jan Koutn├şk, Bas R. Steunebrink, J├╝rgen Schmidhuber

* IEEE Transactions on Neural Networks and Learning Systems ( Volume: 28, Issue: 10, Oct. 2017 ) Pages: 2222 - 2232 
* 12 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

Recurrent Highway Networks


Jul 04, 2017
Julian Georg Zilly, Rupesh Kumar Srivastava, Jan Koutn├şk, J├╝rgen Schmidhuber

* 12 pages, 6 figures, 3 tables 

   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
>>