Peer Reviews of Economics Publications xml
Editorial Board
Susan Athey
Marco Battaglini
Ted Bergstrom
Michele Boldrin
V.V. Chari
Jeff Ely
Drew Fudenberg
Matthew O. Jackson
Jon Levin
David K. Levine
Thomas R. Palfrey
Wolfgang Pesendorfer
Matt Rabin
Debraj Ray
Arthur Robson
Ariel Rubinstein
Jose A. Scheinkman
Ran Spiegler
ISSN 1558-4682
Volume 18 - August 04, 2010 Previous
1. test t. test test2
test2
original link cached copy reviewed by David K. Levine on 08/04/10
2. 1 1. 1 test2
test2
original link cached copy reviewed by David K. Levine on 08/04/10
3. 33 333 test3
test3
original link cached copy reviewed by David K. Levine on 08/04/10
4. test t. test test
test
original link cached copy reviewed by David K. Levine on 08/04/10
5. 111 11 Extensive game theoretic models of reinforcement
Extensive game theoretic models of reinforcement learning assume that players make their decisions by using their experience to evaluate the extensive game strategies. A new and exciting direction of research is being suggested whereby players evaluate each action separately and choose the one with the highest valuation. When applied to win-lose games and when the valuation of an action is assumed to be the payoff received the last time the action was taken, a player with a winning strategy always wins. In the case of general payoffs and when the valuation of an action is assumed to be the average of the payoffs received when the action was taken, the players converge to a subgame perfect equilibrium.
original link cached copy reviewed by David K. Levine on 08/04/10