Non-probabilistic decision making with memory constraints

The single decision maker chooses one of the actions repeatedly. She chooses the action with the highest weighted average of the past payoffs. In the long run either the action with highest expected payoff or the action with highest minimal payoff is chosen depending on how weights evolve.

MoreLess

Year of publication:	2012
Authors:	Vostroknutov, Alexander
Published in:	Economics Letters. - Elsevier, ISSN 0165-1765. - Vol. 117.2012, 1, p. 303-305
Publisher:	Elsevier
Subject:	Adaptive learning \| Constrained memory \| Bandit problems

Online Resource

Check full text access |

More access options

Check Google Scholar

In libraries world-wide (WorldCat)

In German libraries (KVK)

subito order

I need help

More details

Type of publication:	Article
Classification:	D83 - Search, Learning, Information and Knowledge ; D81 - Criteria for Decision-Making under Risk and Uncertainty ; C02 - Mathematical Methods
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10010580441