Display Publications by [Year] [Type] [Topic]
In this chapter, we address how to evolve control strategies for a collective: a set of entities that collectively strives to maximize a global evaluation function that rates the performance of the full system. Addressing such problems by directly applying a global evolutionary algorithm to a population of collectives is unworkable because the search space is prohibitively large. Instead, we focus on evolving each member of the collective separately (i.e., each member has a population from which the individual with the best fitness is selected). The main difficulty with this approach is creating fitness evaluation functions for the members of the collective that will induce the collective to achieve high performance with respect to the system level goal. To overcome this difficulty, we derive member evaluation functions that are both aligned with the global evaluation function (ensuring that members trying to achieve high values of their own fitness function results in a collective with high fitness) and sensitive to the fitness of each member (a member's fitness depends more on its own actions than on actions of other members).
In a difficult rover coordination problem in dynamic and noisy environments, we show how to construct member evaluation functions that lead to good collective behavior. The control policy evolved using aligned and member-sensitive evaluations outperforms global evaluation methods by up to a factor of four. More notably, in the presence of a larger number of rovers or rovers with noisy sensors, the improvements due to the proposed method become significantly more pronounced.
(unavailable)
@incollection{tumer-agogino_ecdue07,
title = {Coordinating Multi-Rover Systems: Evaluation Functions for Dynamic and Noisy Environments},
author = {K. Tumer and A. K. Agogino},
booktitle = {Evolutionary Computation in Dynamic and Uncertain Environments},
editor = {S. Yang},
pages = {371-388},
publisher = {Springer},
abstract = {In this chapter, we address how to evolve control strategies for a collective: a set of entities that collectively strives to maximize a global evaluation function that rates the performance of the full system. Addressing such problems by directly applying a global evolutionary algorithm to a population of collectives is unworkable because the search space is prohibitively large. Instead, we focus on evolving each member of the collective separately (i.e., each member has a population from which the individual with the best fitness is selected). The main difficulty with this approach is creating fitness evaluation functions for the members of the collective that will induce the collective to achieve high performance with respect to the system level goal. To overcome this difficulty, we derive member evaluation functions that are both aligned with the global evaluation function (ensuring that members trying to achieve high values of their own fitness function results in a collective with high fitness) and sensitive to the fitness of each member (a member's fitness depends more on its own actions than on actions of other members).
<p>
In a difficult rover coordination problem in dynamic and noisy environments, we show how to construct member evaluation functions that lead to good collective behavior. The control policy evolved using aligned and member-sensitive evaluations outperforms global evaluation methods by up to a factor of four. More notably, in the presence of a larger number of rovers or rovers with noisy sensors, the improvements due to the proposed method become significantly more pronounced.
},
bib2html_pubtype = {Book Chapters},
bib2html_rescat = {Evolutionary Algorithms, Robotics},
year = {2007}
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 01, 2020 17:39:43