Abstract
Fictitious play and stimulus–response/reinforcement learning are examined in the context of a large population where agents are repeatedly randomly matched. We show that the aggregation of this learning behavior can be qualitatively different from learning at the level of the individual. This aggregate dynamic belongs to the same class of simply defined dynamic as do several formulations of evolutionary dynamics. We obtain sufficient conditions for convergence and divergence which are valid for the whole class of dynamics. These results are therefore robust to most specifications of adaptive behavior.
Original language | English |
---|---|
Pages (from-to) | 79-110 |
Number of pages | 32 |
Journal | Games and Economic Behavior |
Volume | 26 |
Issue number | 1 |
DOIs | |
Publication status | Published - Jan 1999 |
Keywords / Materials (for Non-textual outputs)
- games
- fictitious play
- reinforcement learning
- evolution