Two more classes of games with the continuous-time fictitious play property |
| |
Authors: | Ulrich Berger |
| |
Affiliation: | aVienna University of Economics and Business Administration, Institute VW 5, Augasse 2-6, A-1090 Wien, Austria |
| |
Abstract: | Fictitious Play is the oldest and most studied learning process for games. Since the already classical result for zero-sum games, convergence of beliefs to the set of Nash equilibria has been established for several classes of games, including weighted potential games, supermodular games with diminishing returns, and 3×3 supermodular games. Extending these results, we establish convergence of Continuous-time Fictitious Play for ordinal potential games and quasi-supermodular games with diminishing returns. As a by-product we obtain convergence for 3×m and 4×4 quasi-supermodular games. |
| |
Keywords: | Fictitious play Learning process Ordinal potential games Quasi-supermodular games |
本文献已被 ScienceDirect 等数据库收录! |
|