@inproceedings{b59367ae6a8a407ebfb6857994d9db37,
title = "Evolution of reinforcement learning in uncertain environments: Emergence of risk-aversion and matching",
abstract = "Reinforcement learning (RL) is a fundamental process by which organisms learn to achieve a goal from interactions with the environment. Using Artificial Life techniques we derive (near-)optimal neuronal learning rules in a simple neural network model of decision-making in simulated bumblebees foraging for nectar. The resulting networks exhibit efficient RL, allowing the bees to respond rapidly to changes in reward contingencies. The evolved synaptic plasticity dynamics give rise to varying exploration/exploitation levels from which emerge the welldocumented foraging strategies of risk aversion and probability matching. These are shown to be a direct result of optimal RL, providing a biologically founded, parsimonious and novel explanation for these behaviors. Our results are corroborated by a rigorous mathematical analysis and by experiments in mobile robots.",
author = "Yael Niv and Daphna Joel and Isaac Meilijson and Eytan Ruppin",
note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2001.; 6th European Conference on Advances in Artificial Life, ECAL 2001 ; Conference date: 10-09-2001 Through 14-09-2001",
year = "2001",
doi = "10.1007/3-540-44811-x_27",
language = "English (US)",
isbn = "3540425675",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "252--261",
editor = "Jozef Kelemen and Petr Sosik",
booktitle = "Advances in Artificial Life - 6th European Conference, ECAL 2001, Proceedings",
address = "Germany",
}