Emergence of information processor using real world - Real-time learning of pursuit problem-

Hiroyuki Fujii, Kazuyuki Ito, Akio Gofuku

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Real-time reinforcement learning is difficult because number of trials is too much to complete learning within limited time. To solve the problem, we consider reduction of action-state space by information processor using real world without prior knowledge. We obtain the information processor in evolution by setting the fitness as ease of learning. As a typical example, we address pursuit problem in which dynamics is regarded. As a result, the processor has been obtained in evolution and agent has learned in real-time.

Original languageEnglish
Title of host publicationProceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006
DOIs
Publication statusPublished - 2006
Event6th International Conference on Hybrid Intelligent Systems and 4th Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006 - Auckland, New Zealand
Duration: Dec 13 2006Dec 15 2006

Other

Other6th International Conference on Hybrid Intelligent Systems and 4th Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006
CountryNew Zealand
CityAuckland
Period12/13/0612/15/06

Fingerprint

Reinforcement learning

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Fujii, H., Ito, K., & Gofuku, A. (2006). Emergence of information processor using real world - Real-time learning of pursuit problem-. In Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006 [4041387] https://doi.org/10.1109/HIS.2006.264890

Emergence of information processor using real world - Real-time learning of pursuit problem-. / Fujii, Hiroyuki; Ito, Kazuyuki; Gofuku, Akio.

Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006. 2006. 4041387.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fujii, H, Ito, K & Gofuku, A 2006, Emergence of information processor using real world - Real-time learning of pursuit problem-. in Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006., 4041387, 6th International Conference on Hybrid Intelligent Systems and 4th Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006, Auckland, New Zealand, 12/13/06. https://doi.org/10.1109/HIS.2006.264890
Fujii H, Ito K, Gofuku A. Emergence of information processor using real world - Real-time learning of pursuit problem-. In Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006. 2006. 4041387 https://doi.org/10.1109/HIS.2006.264890
Fujii, Hiroyuki ; Ito, Kazuyuki ; Gofuku, Akio. / Emergence of information processor using real world - Real-time learning of pursuit problem-. Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006. 2006.
@inproceedings{9b230df6b5b74ef28de93a8d2be7b34a,
title = "Emergence of information processor using real world - Real-time learning of pursuit problem-",
abstract = "Real-time reinforcement learning is difficult because number of trials is too much to complete learning within limited time. To solve the problem, we consider reduction of action-state space by information processor using real world without prior knowledge. We obtain the information processor in evolution by setting the fitness as ease of learning. As a typical example, we address pursuit problem in which dynamics is regarded. As a result, the processor has been obtained in evolution and agent has learned in real-time.",
author = "Hiroyuki Fujii and Kazuyuki Ito and Akio Gofuku",
year = "2006",
doi = "10.1109/HIS.2006.264890",
language = "English",
isbn = "0769526624",
booktitle = "Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006",

}

TY - GEN

T1 - Emergence of information processor using real world - Real-time learning of pursuit problem-

AU - Fujii, Hiroyuki

AU - Ito, Kazuyuki

AU - Gofuku, Akio

PY - 2006

Y1 - 2006

N2 - Real-time reinforcement learning is difficult because number of trials is too much to complete learning within limited time. To solve the problem, we consider reduction of action-state space by information processor using real world without prior knowledge. We obtain the information processor in evolution by setting the fitness as ease of learning. As a typical example, we address pursuit problem in which dynamics is regarded. As a result, the processor has been obtained in evolution and agent has learned in real-time.

AB - Real-time reinforcement learning is difficult because number of trials is too much to complete learning within limited time. To solve the problem, we consider reduction of action-state space by information processor using real world without prior knowledge. We obtain the information processor in evolution by setting the fitness as ease of learning. As a typical example, we address pursuit problem in which dynamics is regarded. As a result, the processor has been obtained in evolution and agent has learned in real-time.

UR - http://www.scopus.com/inward/record.url?scp=40249090262&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=40249090262&partnerID=8YFLogxK

U2 - 10.1109/HIS.2006.264890

DO - 10.1109/HIS.2006.264890

M3 - Conference contribution

AN - SCOPUS:40249090262

SN - 0769526624

SN - 9780769526621

BT - Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006

ER -