18/11/2020

Foolproof cooperative learning

Alexis Jacq, Julien Perolat, Matthieu Geist, Olivier Pietquin

Keywords:

Abstract Paper Similar Papers

Abstract: This paper extends the notion of learning algorithms and learning equilibriums from repeated games theory to stochastic games. We introduce Foolproof Cooperative Learning (FCL), an algorithm that converges to an equilibrium strategy that allows cooperative strategies in self-play setting while being not exploitable by selfish learners. By construction, FCL is a learning equilibrium for repeated symmetric games. We illustrate the behavior of FCL on symmetric matrix and grid games, and its robustness to selfish learners.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ACML 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 13:17 
 0
 0
 0
 0
 5:36 
 0
 0
 0
 0
 15:16 
 0
 0
 0
 0
 15:35 
 0
 0
 0
 0
 11:52 
 0
 0
 0
 0
 5:24 
 0
 0
 0
 0
 17:04 
 0
 0
 0
 0
 5:24 
 0
 0
 0
 0
 5:28 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 2:47 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 0
 15:14 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 5:22 
 1
 0
 0
 1
 5:15 
 0
 0
 0
 0
 15:58 
 0
 0
 0
 0
 20:14 
 0
 0
 0
 0
 13:47 
 0
 0
 0
 0
 14:11 
 0
 0
 0
 0
 14:28 
 0
 0
 0
 0
 12:55 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 16:40 
 0
 0
 0
 0
 12:31 
 0
 0
 0
 0
 14:59 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 3:04 
 0
 0
 0
 0
 14:29 
 0
 0
 0
 0
 6:00 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 12:05 
 0
 0
 0
 0
 4:54 
 0
 0
 0
 0
 3:30 
 0
 0
 0
 0
 14:26 
 0
 0
 0
 0
 16:01 
 0
 0
 0
 1
 5:12 
 0
 0
 0
 0
 5:16 
 0
 0
 0
 0
 16:43