We describe a general model, 'experience-weighted attraction' (EWA) learning, which includes reinforcement learning and a class of weighted fictitious play belief models as special cases. In EWA, strategies have attractions which reflect prior predispositions, are updated based on payoff experience, and determine choice probabilities according to some rule (e.g., logit). A key feature is a parameter δ which weights the strength of hypothetical reinforcement of strategies which were not chosen according to the payoff they would have yielded. When δ = 0 choice reinforcement results. When δ = 1, levels of reinforcement of strategies are proportional to expected payoffs given beliefs based on past history. Another key feature is the growth rates of attractions. The EWA model controls the growth rates by two decay parameters, φ and ρ, which depreciate attractions and amount of experience separately. When φ = ρ belief-based models result; when ρ = 0 choice reinforcement results. Using three data sets, parameter estimates of the model were calibrated on part of the data and used to predict the rest. Estimates of δ are generally around .50, φ around 1, and ρ varies from 0 to φ. Choice reinforcement models often outperform belief-based models in the calibration phase and underperform in out-of-sample validation. Both special cases are generally rejected in favor of EWA, though sometimes belief models do better. EWA is able to combine the best features of both approaches, allowing attractions to begin and grow exibly as choice reinforcement does, but reinforcing unchosen strategies substantially as belief-based models implicitly do.
Download Info
To download:
If you experience problems downloading a file, check if you have the
proper application to
view it first. Information about this may be contained
in the File-Format links below. In case of further problems read
the IDEAS help
page. Note that these files are not on the IDEAS
site. Please be patient as the files may be large.
Publisher Info
Paper provided by California Institute of Technology, Division of the Humanities and Social Sciences in its series Working Papers with number
1003.
Length: 42 pages Date of creation: Mar 1997 Date of revision: Handle: RePEc:clt:sswopa:1003
Contact details of provider: Postal: Working Paper Assistant, Division of the Humanities and Social Sciences, 228-77, Caltech, Pasadena CA 91125 Phone: 626 395-4065 Fax: 626 405-9841 Email: Web page: http://www.hss.caltech.edu/ss
Order Information: Postal: Working Paper Assistant, Division of the Humanities and Social Sciences, 228-77, Caltech, Pasadena CA 91125 Email:
For technical questions regarding this item, or to correct its listing, contact: (Victoria Mason).
References listed on IDEAS Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
Cited by: (explanations, Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.)
Andreas Blume & Douglas V. DeJong & George R. Neumann & Nathan E. Savin, 1998.
"Learning in Sender-Receiver Games,"
CIG Working Papers
FS IV 98-13, Wissenschaftszentrum Berlin (WZB), Research Unit: Competition and Innovation (CIG).
[Downloadable!]