2 search results - page 1 / 1 » Polynomial Time Prediction Strategy with Almost Optimal Mist... |
COLT
2004
Springer
15 years 2 months ago
2004
Springer
We give the first polynomial time prediction strategy for any PAC-learnable class C that probabilistically predicts the target with mistake probability poly(log(t)) t = ˜O 1 t w...
IPCO
2010
14 years 11 months ago
2010
Abstract. We consider two-person zero-sum stochastic mean payoff games with perfect information, or BWR-games, given by a digraph G = (V = VB VW VR, E), with local rewards r : E R...