@misc{10481/77969,
year = {2015},
month = {9},
url = {https://hdl.handle.net/10481/77969},
abstract = {Adversarial decision making is aimed at determining strategies to anticipate the behavior of an opponent trying to learn from
our actions. One defense is to make decisions intended to confuse the opponent, although our rewards can be diminished.
This idea has already been captured in an adversarial model introduced in a previous work, in which two agents separately
issue responses to an unknown sequence of external inputs. Each agent’s reward depends on the current input and the
responses of both agents. In this contribution, (a) we extend the original model by establishing stochastic dependence
between an agent’s responses and the next input of the sequence, and (b) we study the design of time varying decision
strategies for the extended model. The strategies obtained are compared against static strategies from theoretical and
empirical points of view. The results show that time varying strategies outperform static ones.},
organization = {Ministry of Science and Innovation, Spain (MICINN)
Spanish Government	TIN2011-27696-C02-01},
organization = {Andalusian government	P11-TIC-8001},
organization = {CEI-Biotic Granada	GENIL-PYR-2014-9},
organization = {European Commission},
organization = {German Research Foundation (DFG)},
publisher = {Sciendo},
keywords = {Adversarial decision making},
keywords = {Imitation},
keywords = {Strategies},
keywords = {State dependence},
keywords = {Reward},
keywords = {Inteligencia artificial},
keywords = {Artificial intelligence},
title = {A repeated imitation model with dependence between stages: decision strategies and rewards},
doi = {10.1515/amcs-2015-0045},
author = {Villacorta Iglesias, Pablo José and Pelta Mochcovsky, David Alejandro},
}