
Melioration Learning in Two-Person Games
Author(s) -
Johannes Zschache
Publication year - 2016
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0166708
Subject(s) - nash equilibrium , reinforcement learning , convergence (economics) , mathematical economics , fictitious play , computer science , best response , game theory , artificial intelligence , mathematics , economics , economic growth
Melioration learning is an empirically well-grounded model of reinforcement learning. By means of computer simulations, this paper derives predictions for several repeatedly played two-person games from this model. The results indicate a likely convergence to a pure Nash equilibrium of the game. If no pure equilibrium exists, the relative frequencies of choice may approach the predictions of the mixed Nash equilibrium. Yet in some games, no stable state is reached.