24 search results - page 1 / 5 » On No-Regret Learning, Fictitious Play, and Nash Equilibrium |
ICML
2001
IEEE
14 years 5 months ago
2001
IEEE
COLT
2003
Springer
13 years 9 months ago
2003
Springer
A general class of no-regret learning algorithms, called no-Φ-regret learning algorithms, is defined which spans the spectrum from no-external-regret learning to no-internal-reg...
LAMAS
2005
Springer
13 years 9 months ago
2005
Springer
We present a new multiagent learning algorithm, RVσ(t), that builds on an earlier version, ReDVaLeR . ReDVaLeR could guarantee (a) convergence to best response against stationary ...
ANOR
2005
13 years 4 months ago
2005
The main objects here are finite-strategy games in which entropic terms are subtracted from the payoffs. After such subtraction each Nash equilibrium solves an explicit, unconstra...
SAGT
2010
Springer
13 years 2 months ago
2010
Springer
Fictitious play is a simple learning algorithm for strategic games that proceeds in rounds. In each round, the players play a best response to a mixed strategy that is given by the...