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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Over-communicate no more: Situated RL agents learn concise communication protocols


Nov 02, 2022
Aleksandra Kalinowska, Elnaz Davoodi, Florian Strub, Kory W Mathewson, Ivana Kajic, Michael Bowling, Todd D Murphey, Patrick M Pilarski


   Access Paper or Ask Questions

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

Interpolating Between Softmax Policy Gradient and Neural Replicator Dynamics with Capped Implicit Exploration


Jun 04, 2022
Dustin Morrill, Esra'a Saleh, Michael Bowling, Amy Greenwald

* At Reinforcement Learning and Decision Making 2022, June 2022. 9 pages and 1 figure 

   Access Paper or Ask Questions

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

Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games: Corrections


May 24, 2022
Dustin Morrill, Ryan D'Orazio, Marc Lanctot, James R. Wright, Michael Bowling, Amy R. Greenwald

* This is a version of arXiv:2102.06973 showing corrections to the official version published at ICML 2021. 45 pages and 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

Should Models Be Accurate?


May 22, 2022
Esra'a Saleh, John D. Martin, Anna Koop, Arash Pourzarabi, Michael Bowling

* The 5th Multidisciplinary Conference on Reinforcement Learning and Decision Making ( RLDM 2022 ) 

   Access Paper or Ask Questions

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

Player of Games


Dec 06, 2021
Martin Schmid, Matej Moravcik, Neil Burch, Rudolf Kadlec, Josh Davidson, Kevin Waugh, Nolan Bard, Finbarr Timbers, Marc Lanctot, Zach Holland, Elnaz Davoodi, Alden Christianson, Michael Bowling


   Access Paper or Ask Questions

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

The Partially Observable History Process


Nov 15, 2021
Dustin Morrill, Amy R. Greenwald, Michael Bowling

* 8 pages, 2 figures 

   Access Paper or Ask Questions

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

Learning to Be Cautious


Oct 29, 2021
Montaser Mohammedalamen, Dustin Morrill, Alexander Sieusahai, Yash Satsangi, Michael Bowling


   Access Paper or Ask Questions

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

Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games


Feb 13, 2021
Dustin Morrill, Ryan D'Orazio, Marc Lanctot, James R. Wright, Michael Bowling, Amy Greenwald

* 32 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

Solving Common-Payoff Games with Approximate Policy Iteration


Jan 11, 2021
Samuel Sokota, Edward Lockhart, Finbarr Timbers, Elnaz Davoodi, Ryan D'Orazio, Neil Burch, Martin Schmid, Michael Bowling, Marc Lanctot

* AAAI 2021 

   Access Paper or Ask Questions

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

Hindsight and Sequential Rationality of Correlated Play


Dec 17, 2020
Dustin Morrill, Ryan D'Orazio, Reca Sarfati, Marc Lanctot, James R. Wright, Amy Greenwald, Michael Bowling

* Technical report for a paper to appear at AAAI 2021. 26 pages, 15 figures 

   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
>>