A Reward-driven Model of Darwinian Fitness
Jan Teichmann, Eduardo Alonso, Mark Broom
2015
Abstract
In this paper we present a model that, based on the principle of total energy balance (similar to energy conservation in Physics), bridges the gap between Darwinian fitness theories and reward-driven theories of behaviour. Results show that it is possible to accommodate the reward maximization principle underlying modern approaches in behavioural reinforcement learning and traditional fitness approaches. Our framework, presented within a prey-predator model, may have important consequences in the study of behaviour.
DownloadPaper Citation
in Harvard Style
Teichmann J., Alonso E. and Broom M. (2015). A Reward-driven Model of Darwinian Fitness . In Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 1: ECTA, ISBN 978-989-758-157-1, pages 174-179. DOI: 10.5220/0005591501740179
in Bibtex Style
@conference{ecta15,
author={Jan Teichmann and Eduardo Alonso and Mark Broom},
title={A Reward-driven Model of Darwinian Fitness},
booktitle={Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 1: ECTA,},
year={2015},
pages={174-179},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005591501740179},
isbn={978-989-758-157-1},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 1: ECTA,
TI - A Reward-driven Model of Darwinian Fitness
SN - 978-989-758-157-1
AU - Teichmann J.
AU - Alonso E.
AU - Broom M.
PY - 2015
SP - 174
EP - 179
DO - 10.5220/0005591501740179