Learning and decision costs in one-person games
โ Scribed by Charles Romeo; Barry Sopher
- Publisher
- John Wiley and Sons
- Year
- 1999
- Tongue
- English
- Weight
- 227 KB
- Volume
- 14
- Category
- Article
- ISSN
- 0883-7252
No coin nor oath required. For personal study only.
โฆ Synopsis
This paper reports the results of a two-part data analysis of learning in a repeated costly decision experiment. In the ยฎrst part we test payo dominance under the hypothesis of expected payo maximization. We utilize a dynamic probability distribution over decisions for each player, characterizing what each player has learned about the payo function by the moments from these distributions. In the second part, we test the hypothesis of expected payo maximization for players in each treatment group. Expected payo maximization is supported but payo dominance is not.
๐ SIMILAR VOLUMES
Thirty-six subjects participated in two-person zero-sum games played against an experimenter in an examination of the effect of different types of game matrices and different mixed strategies on behavior. Results showed that when the opponent played nonoptimally, subjects were able to detect this no
This paper gives a formulation of a theory of n-person cooperative games with side payments in t e r m s of a partition function which i s defined on the s e t of all partitions of the s e t of players. The r e s u l t s for all games with n 5 3 a r e presented. This development generalizes the von
In a recent paper Kinber, Smith, Velauthapillai, and Wiehagen introduced a new notion of ``parallel learning.'' They call a set S of functions (m, n)-learnable if there is a learning machine which for any n-tuple of pairwise distinct functions from S learns at least m functions correctly from exampl