Strategy Learning in 3x3 Games by Neural Networks
Zizzo, D. J.
Cambridge Working Papers in Economics
Faculty of Economics
MetadataShow full item record
Sgroi, D., & Zizzo, D. J. (2004). Strategy Learning in 3x3 Games by Neural Networks. https://doi.org/10.17863/CAM.5448
This paper presents a neural network based methodology for examining the learning of game-playing rules in never-before seen games. A network is trained to pick Nash equilibria in a set of games and then released to play a larger set of new games. While faultlessly selecting Nash equilibria in never-before seen games is too complex a task for the network, Nash equilibria are chosen approximately 60% of the times. Furthermore, despite training the network to select Nash equilibria, what emerges are endogenously obtained bounded-rational rules which are closer to payoff dominance, and the best response to payoff dominance.
Classification-JEL: C72, D00, D83, rationality, learning, neural networks, normal form games, complexity
This record's DOI: https://doi.org/10.17863/CAM.5448
All Rights Reserved
Licence URL: https://www.rioxx.net/licenses/all-rights-reserved/