Level-0 Meta-Models for Predicting Human Behavior in Games
Full Text: 2600057.2602907.pdf
Behavioral game theory seeks to describe the way actual people (as compared to idealized, “rational” agents)act in strategic situations. Our own recent work has identified iterative models (such as quantal cognitive hierarchy) as the state of the art for predicting human play in unrepeated, simultaneous-move games [Wright and Leyton-Brown 2012]. Iterative models predict that agents reason iteratively about their opponents, building up from a specification of nonstrategic behavior called level-0. The modeler is in principle free to choose any description of level-0 behavior that makes sense for the given setting; however, in practice al-most all existing work specifies this behavior as a uniform distribution over actions. In most games it is not plausible that even nonstrategic agents would choose an action uniformly at random, nor that other agents would expect them to do so. A more accurate model for level-0 behavior has the potential to dramatically improve predictions of human behavior, since a substantial fraction of agents may play level-0 strategies directly, and furthermore since iterative models ground all higher-level strategies in responses to the level-0strategy. Our work considers “meta-models” of level-0 behavior: models of the way in which level-0 agents construct a probability distribution over actions, given an arbitrary game. We evaluated many such meta-models, each of which makes its prediction based only on general features that can be computed from any normal form game. We evaluated the effects of combining each new level-0 meta-model with various iterative models, and in many cases observed large improvements in the models’ predictive accuracies. In the end, we recommend a meta-model that achieved excellent performance across the board: a linear weighting of features that requires the estimation of five weights.
Citation
J. Wright, K. Leyton-Brown. "Level-0 Meta-Models for Predicting Human Behavior in Games". ACM Conference on Economics and Computation, Palo Alto, USA, (ed: Moshe Babaioff, Vincent Conitzer, David A. Easley), pp 857-873, June 2014.| Keywords: | Behavioral game theory, bounded rationality, game theory, cognitive models, cognitive hierarchy, level-k, prediction |
| Category: | In Conference |
| Web Links: | ACM Digital Library |
| DOI |
BibTeX
@incollection{Wright+Leyton-Brown:14,
author = {James R. Wright and Kevin Leyton-Brown},
title = {Level-0 Meta-Models for Predicting Human Behavior in Games},
Editor = {Moshe Babaioff, Vincent Conitzer, David A. Easley},
Pages = {857-873},
booktitle = {ACM Conference on Economics and Computation},
year = 2014,
}Last Updated: March 03, 2020Submitted by Sabina P
