Payoff size variation problem in simple reinforcement learning algorithms

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14560%2F13%3A00074742" target="_blank" >RIV/00216224:14560/13:00074742 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Payoff size variation problem in simple reinforcement learning algorithms
Original language description
This paper shows that the speed of the reinforcement learning depends on the size of the payoffs, at least when all payoffs are positive. When the speed of learning is too fast, the agents tend to learn to play the actions which they randomly chosen in the first rounds of the learning process. The compositions of the agents? strategies then on the aggregate level resembles the initial individual agent?s mixed strategy. This may create artificial effects in the simulations where the size of payoffs depend on the model treatments because the speed of learning cannot be tuned in.
Czech name
—
Czech description
—

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 31st International Conference Mathematical Methods in Economics 2013
ISBN
9788087035764
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
518-523
Publisher name
College of Polytechnics Jihlava
Place of publication
Jihlava
Event location
Jihlava
Event date
Jan 1, 2013
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
000335578000088

Similar results(10)