Proceedings of the 2nd International Conference on Applied Social Science Research

Modified Reinforcement Learning Infrastructure

Authors
Jyrki Suomala, Ville Suomala
Corresponding Author
Jyrki Suomala
Available Online July 2014.
DOI
https://doi.org/10.2991/icassr-14.2014.27How to use a DOI?
Keywords
MRLI, Graph Theory, Learning, Behavioural model, Decision-making.
Abstract
The reinforcement learning (RL) model has been very successful in behavioural sciences, artificial intelligence and neuro- science. Despite its fruitfulness in many simple situations, the RL model does not always cope well with real life situations involving a large space of possible world states or a large set of possible actions. We propose a modified version of the RL learning model. The benefit of this model is that the temporal difference prediction error can be used directly to update not only the value of the latest action of the learning agent, but the values of many possible future actions. An example application of this modified reinforcement learning infrastructure (MRLI) is presented for a customer behaviour in a complex shopping environment.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Volume Title
Proceedings of the 2nd International Conference on Applied Social Science Research
Series
Advances in Intelligent Systems Research
Publication Date
July 2014
ISBN
978-94-62520-24-0
ISSN
1951-6851
DOI
https://doi.org/10.2991/icassr-14.2014.27How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Jyrki Suomala
AU  - Ville Suomala
PY  - 2014/07
DA  - 2014/07
TI  - Modified Reinforcement Learning Infrastructure
BT  - Proceedings of the 2nd International Conference on Applied Social Science Research
PB  - Atlantis Press
SP  - 95
EP  - 97
SN  - 1951-6851
UR  - https://doi.org/10.2991/icassr-14.2014.27
DO  - https://doi.org/10.2991/icassr-14.2014.27
ID  - Suomala2014/07
ER  -