-
On Local Regret
Online learning aims to perform nearly as well as the best hypothesis in...
06/14/2012 ∙ by Michael Bowling, et al. ∙
0
∙
share
read it
-
No-Regret Learning in Extensive-Form Games with Imperfect Recall
Counterfactual Regret Minimization (CFR) is an efficient no-regret learn...
05/03/2012 ∙ by Marc Lanctot, et al. ∙
0
∙
share
read it
-
Slow Learners are Fast
Online learning algorithms have impressive convergence properties when i...
11/03/2009 ∙ by John Langford, et al. ∙
0
∙
share
read it
