Evolving internal memory for T-maze tasks in noisy environments

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In autonomous agent systems, internal memory can be an important element to overcome the limitations of purely reactive agent behaviour. This paper presents an analysis of memory requirements for T-maze tasks well known as the road sign problem. In these tasks, a robot agent should make a decision about turning left or right at the T-junction in the approach corridor, depending on a history of perceptions. The robot agent in simulation can sense the light intensity influenced by light lamps placed on the bank of the wall. We apply the evolutionary multiobjective optimization approach to finite state controllers with two objectives: behaviour performance and memory size. Then the internal memory is quantified by counting internal states needed for the T-maze tasks in noisy environments. In particular, we focused on the influence of noise on internal memory and behaviour performance, and it is shown that state machines with variable thresholds can improve the performance with a hysteresis effect to filter out noise. This paper also provides an analysis of noise effect on perceptions and its relevance on performance degradation in state machines.

Original languageEnglish
Pages (from-to)183-210
Number of pages28
JournalConnection Science
Volume16
Issue number3
DOIs
Publication statusPublished - 2004 Sep 1

Fingerprint

Data storage equipment
Robots
Autonomous agents
Multiobjective optimization
Electric lamps
Chemical elements
Hysteresis
Degradation
Controllers

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Artificial Intelligence

Cite this

@article{10223356c48a4bfb969639951d02a487,
title = "Evolving internal memory for T-maze tasks in noisy environments",
abstract = "In autonomous agent systems, internal memory can be an important element to overcome the limitations of purely reactive agent behaviour. This paper presents an analysis of memory requirements for T-maze tasks well known as the road sign problem. In these tasks, a robot agent should make a decision about turning left or right at the T-junction in the approach corridor, depending on a history of perceptions. The robot agent in simulation can sense the light intensity influenced by light lamps placed on the bank of the wall. We apply the evolutionary multiobjective optimization approach to finite state controllers with two objectives: behaviour performance and memory size. Then the internal memory is quantified by counting internal states needed for the T-maze tasks in noisy environments. In particular, we focused on the influence of noise on internal memory and behaviour performance, and it is shown that state machines with variable thresholds can improve the performance with a hysteresis effect to filter out noise. This paper also provides an analysis of noise effect on perceptions and its relevance on performance degradation in state machines.",
author = "DaeEun Kim",
year = "2004",
month = "9",
day = "1",
doi = "10.1080/09540090412331314812",
language = "English",
volume = "16",
pages = "183--210",
journal = "Connection Science",
issn = "0954-0091",
publisher = "Taylor and Francis AS",
number = "3",

}

Evolving internal memory for T-maze tasks in noisy environments. / Kim, DaeEun.

In: Connection Science, Vol. 16, No. 3, 01.09.2004, p. 183-210.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evolving internal memory for T-maze tasks in noisy environments

AU - Kim, DaeEun

PY - 2004/9/1

Y1 - 2004/9/1

N2 - In autonomous agent systems, internal memory can be an important element to overcome the limitations of purely reactive agent behaviour. This paper presents an analysis of memory requirements for T-maze tasks well known as the road sign problem. In these tasks, a robot agent should make a decision about turning left or right at the T-junction in the approach corridor, depending on a history of perceptions. The robot agent in simulation can sense the light intensity influenced by light lamps placed on the bank of the wall. We apply the evolutionary multiobjective optimization approach to finite state controllers with two objectives: behaviour performance and memory size. Then the internal memory is quantified by counting internal states needed for the T-maze tasks in noisy environments. In particular, we focused on the influence of noise on internal memory and behaviour performance, and it is shown that state machines with variable thresholds can improve the performance with a hysteresis effect to filter out noise. This paper also provides an analysis of noise effect on perceptions and its relevance on performance degradation in state machines.

AB - In autonomous agent systems, internal memory can be an important element to overcome the limitations of purely reactive agent behaviour. This paper presents an analysis of memory requirements for T-maze tasks well known as the road sign problem. In these tasks, a robot agent should make a decision about turning left or right at the T-junction in the approach corridor, depending on a history of perceptions. The robot agent in simulation can sense the light intensity influenced by light lamps placed on the bank of the wall. We apply the evolutionary multiobjective optimization approach to finite state controllers with two objectives: behaviour performance and memory size. Then the internal memory is quantified by counting internal states needed for the T-maze tasks in noisy environments. In particular, we focused on the influence of noise on internal memory and behaviour performance, and it is shown that state machines with variable thresholds can improve the performance with a hysteresis effect to filter out noise. This paper also provides an analysis of noise effect on perceptions and its relevance on performance degradation in state machines.

UR - http://www.scopus.com/inward/record.url?scp=10244246722&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10244246722&partnerID=8YFLogxK

U2 - 10.1080/09540090412331314812

DO - 10.1080/09540090412331314812

M3 - Article

AN - SCOPUS:10244246722

VL - 16

SP - 183

EP - 210

JO - Connection Science

JF - Connection Science

SN - 0954-0091

IS - 3

ER -