Sciweavers

Share
warning: Creating default object from empty value in /var/www/modules/taxonomy/taxonomy.module on line 1416.
AAAI
2007
11 years 3 months ago
Thresholded Rewards: Acting Optimally in Timed, Zero-Sum Games
In timed, zero-sum games, the goal is to maximize the probability of winning, which is not necessarily the same as maximizing our expected reward. We consider cumulative intermedi...
Colin McMillen, Manuela M. Veloso
ICML
2003
IEEE
12 years 2 months ago
BL-WoLF: A Framework For Loss-Bounded Learnability In Zero-Sum Games
We present BL-WoLF, a framework for learnability in repeated zero-sum games where the cost of learning is measured by the losses the learning agent accrues (rather than the number...
Vincent Conitzer, Tuomas Sandholm
books