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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Efficient Planning in a Compact Latent Action Space


Aug 25, 2022
Zhengyao Jiang, Tianjun Zhang, Michael Janner, Yueying Li, Tim RocktÀschel, Edward Grefenstette, Yuandong Tian

* Code available at https://github.com/ZhengyaoJiang/latentplan 

   Access Paper or Ask Questions

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

Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning


Jul 23, 2022
Michael Matthews, Mikayel Samvelyan, Jack Parker-Holder, Edward Grefenstette, Tim RocktÀschel

* 19 pages, 12 figures, to be published in the Conference on Lifelong Learning Agents 2022 

   Access Paper or Ask Questions

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

Grounding Aleatoric Uncertainty in Unsupervised Environment Design


Jul 11, 2022
Minqi Jiang, Michael Dennis, Jack Parker-Holder, Andrei Lupu, Heinrich KĂŒttler, Edward Grefenstette, Tim RocktĂ€schel, Jakob Foerster


   Access Paper or Ask Questions

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

Graph Backup: Data Efficient Backup Exploiting Markovian Transitions


May 31, 2022
Zhengyao Jiang, Tianjun Zhang, Robert Kirk, Tim RocktÀschel, Edward Grefenstette


   Access Paper or Ask Questions

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

Insights From the NeurIPS 2021 NetHack Challenge


Mar 22, 2022
Eric Hambro, Sharada Mohanty, Dmitrii Babaev, Minwoo Byeon, Dipam Chakraborty, Edward Grefenstette, Minqi Jiang, Daejin Jo, Anssi Kanervisto, Jongmin Kim, Sungwoong Kim, Robert Kirk, Vitaly Kurin, Heinrich KĂŒttler, Taehwon Kwon, Donghoon Lee, Vegard Mella, Nantas Nardelli, Ivan Nazarov, Nikita Ovsov, Jack Parker-Holder, Roberta Raileanu, Karolis Ramanauskas, Tim RocktĂ€schel, Danielle Rothermel, Mikayel Samvelyan, Dmitry Sorokin, Maciej Sypetkowski, MichaƂ Sypetkowski

* Under review at PMLR for the NeuRIPS 2021 Competition Workshop Track, 10 pages + 10 in appendices 

   Access Paper or Ask Questions

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

Evolving Curricula with Regret-Based Environment Design


Mar 08, 2022
Jack Parker-Holder, Minqi Jiang, Michael Dennis, Mikayel Samvelyan, Jakob Foerster, Edward Grefenstette, Tim RocktÀschel

* First two authors contributed equally 

   Access Paper or Ask Questions

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

Improving Intrinsic Exploration with Language Abstractions


Feb 17, 2022
Jesse Mu, Victor Zhong, Roberta Raileanu, Minqi Jiang, Noah Goodman, Tim RocktÀschel, Edward Grefenstette


   Access Paper or Ask Questions

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

A Survey of Generalisation in Deep Reinforcement Learning


Nov 18, 2021
Robert Kirk, Amy Zhang, Edward Grefenstette, Tim RocktÀschel


   Access Paper or Ask Questions

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

Replay-Guided Adversarial Environment Design


Oct 06, 2021
Minqi Jiang, Michael Dennis, Jack Parker-Holder, Jakob Foerster, Edward Grefenstette, Tim RocktÀschel

* NeurIPS 2021 

   Access Paper or Ask Questions

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

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research


Sep 27, 2021
Mikayel Samvelyan, Robert Kirk, Vitaly Kurin, Jack Parker-Holder, Minqi Jiang, Eric Hambro, Fabio Petroni, Heinrich KĂŒttler, Edward Grefenstette, Tim RocktĂ€schel

* NeurIPS 2021: Datasets and Benchmarks Track 

   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
4
5
>>