Context-Dependent Reinforcement Learning

Oussama H. Hamid

2016

Abstract

This project, entitled ‘Context-Dependent Reinforcement Learning’ was a subproject within the cluster project ‘Neurobiologically Inspired Multimodal Recognition for Technical Communication Systems’, which was funded by the State of Saxony-Anhalt and the Federal Ministry of Education and Research (BMBF) in the Federal Republic of Germany. The aim of the subproject was to extend to human observers Miyahsita’s classical experiments with non-human primates on the learning of arbitrary visuomotor associations. In addition to experimental work, we developed a series of computational models of reinforcement learning with increasing complexity. In the most sophisticated variant, the learning rate depends on predictiveness, i.e., the more predictive an event, the more slowly its weight is adjusted). Besides reproducing the corresponding behavioral data, these models proved enormously helpful in developing our thinking in regards to the underlying processes, i.e., the plasticity and dynamics of attractor neural network models of associative learning.

Paper Citation

in Harvard Style

H. Hamid O. (2015). Context-Dependent Reinforcement Learning.In European Projects in Knowledge Applications and Intelligent Systems - Volume 1: EPS Lisbon 2016, ISBN 978-989-758-356-8, pages 111-134. DOI: 10.5220/0007901201110134

in Bibtex Style

@conference{eps lisbon 201615,
author={Oussama H. Hamid},
title={Context-Dependent Reinforcement Learning},
booktitle={European Projects in Knowledge Applications and Intelligent Systems - Volume 1: EPS Lisbon 2016,},
year={2015},
pages={111-134},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007901201110134},
isbn={978-989-758-356-8},
}

in EndNote Style

TY - CONF

JO - European Projects in Knowledge Applications and Intelligent Systems - Volume 1: EPS Lisbon 2016,
TI - Context-Dependent Reinforcement Learning
SN - 978-989-758-356-8
AU - H. Hamid O.
PY - 2015
SP - 111
EP - 134
DO - 10.5220/0007901201110134