<?xml version='1.0' encoding='UTF-8'?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-05-11T14:26:42Z</responseDate>
  <request metadataPrefix="oai_dc" verb="GetRecord" identifier="oai:ipsj.ixsq.nii.ac.jp:00234937">https://ipsj.ixsq.nii.ac.jp/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:ipsj.ixsq.nii.ac.jp:00234937</identifier>
        <datestamp>2025-01-19T09:39:55Z</datestamp>
        <setSpec>1164:2735:11468:11669</setSpec>
      </header>
      <metadata>
        <oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns="http://www.w3.org/2001/XMLSchema" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
          <dc:title>階層強化学習を用いた四脚ロボットの異なる床環境に対する歩行方策適応</dc:title>
          <dc:title>Adaptation of walking strategies to diﬀerent ground conditions for a quadruped robot using hierarchical reinforcement learning</dc:title>
          <dc:creator>甲斐, 舜也</dc:creator>
          <dc:creator>八木, 聡明</dc:creator>
          <dc:creator>後藤, 祐汰</dc:creator>
          <dc:creator>山森, 聡</dc:creator>
          <dc:creator>森本, 淳</dc:creator>
          <dc:creator>Shunya, Kai</dc:creator>
          <dc:creator>Satoshi, Yagi</dc:creator>
          <dc:creator>Yuta, Goto</dc:creator>
          <dc:creator>Satoshi, Yamamori</dc:creator>
          <dc:creator>Jun, Morimoto</dc:creator>
          <dc:subject>ニューロコンピューティング2</dc:subject>
          <dc:description>本研究では，四脚ロボットの歩行課題を例に，異なる床環境への適応を可能にするためのアプローチを検討した．具体的には，異なる環境において獲得した基底となる下層方策群を準備し，その下層方策の組み合わせによって，新たな環境に対応することを試みた．その組み合わせ戦略が上位階層が経験を通じて獲得するような階層強化学習手法を提案する．これにより，限られた試行回数で異なる環境において歩行運動生成を達成する方策が獲得できることを示した．</dc:description>
          <dc:description>In this study, an approach to enable adaptation to diﬀerent ground conditions was explored using the walking task of a quadruped robot as an example. Speciﬁcally, we prepared low-level policies acquired in diﬀerent conditions and attempted to adapt to new environments by combining these low-level policies. We propose a hierarchical reinforcement learning method in which the combined strategies are acquired by the upper-level policy through learning iterations. We show that proposed approach allows the acquisition of policies for generating walking movements in diﬀerent environments with a limited number of learning trials.</dc:description>
          <dc:description>technical report</dc:description>
          <dc:publisher>情報処理学会</dc:publisher>
          <dc:date>2024-06-13</dc:date>
          <dc:format>application/pdf</dc:format>
          <dc:identifier>研究報告数理モデル化と問題解決（MPS）</dc:identifier>
          <dc:identifier>50</dc:identifier>
          <dc:identifier>2024-MPS-148</dc:identifier>
          <dc:identifier>1</dc:identifier>
          <dc:identifier>5</dc:identifier>
          <dc:identifier>2188-8833</dc:identifier>
          <dc:identifier>AN10505667</dc:identifier>
          <dc:identifier>https://ipsj.ixsq.nii.ac.jp/record/234937/files/IPSJ-MPS24148050.pdf</dc:identifier>
          <dc:language>jpn</dc:language>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
