Behavior Learning Based on a Policy Gradient Method: Separation of Environmental Dynamics and State Values in Policies

Research output: Contribution to journalArticle

1 Citation (Scopus)
Original languageEnglish
Pages (from-to)164-174
JournalPRICAI2008, Proceedings Lecture Notes in Computer Science
Volume5351
Publication statusPublished - 2008 Dec 19

Cite this

@article{837f1df8e0544521b84667aa0d23c5a7,
title = "Behavior Learning Based on a Policy Gradient Method: Separation of Environmental Dynamics and State Values in Policies",
author = "Seiji Ishihara and Igarashi, {Seiji Ishihara;Harukazu}",
year = "2008",
month = "12",
day = "19",
language = "English",
volume = "5351",
pages = "164--174",
journal = "PRICAI2008, Proceedings Lecture Notes in Computer Science",

}

TY - JOUR

T1 - Behavior Learning Based on a Policy Gradient Method: Separation of Environmental Dynamics and State Values in Policies

AU - Ishihara, Seiji

AU - Igarashi, Seiji Ishihara;Harukazu

PY - 2008/12/19

Y1 - 2008/12/19

M3 - Article

VL - 5351

SP - 164

EP - 174

JO - PRICAI2008, Proceedings Lecture Notes in Computer Science

JF - PRICAI2008, Proceedings Lecture Notes in Computer Science

ER -