1 Ocak 2022 Dergi makalesi Açık Erişim

Ada, Suzan Ece; Ugur, Emre; Akin, H. Levent

MARC21 XML

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">user-tubitak-destekli-proje-yayinlari</subfield>
    <subfield code="o">oai:aperta.ulakbim.gov.tr:253575</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">In this paper, we propose a set of robust training methods for deep reinforcement learning to transfer learning acquired in one control task to a set of previously unseen control tasks. We improve generalization in commonly used transfer learning benchmarks by a novel sample elimination technique, early stopping, and maximum entropy adversarial reinforcement learning. To generate robust policies, we use sample elimination during training via a method we call strict clipping. We apply early stopping, a method previously used in supervised learning, to deep reinforcement learning. Subsequently, we introduce maximum entropy adversarial reinforcement learning to increase the domain randomization during training for a better target task performance. Finally, we evaluate the robustness of these methods compared to previous work on simulated robots in target environments where the gravity, the morphology of the robot, and the tangential friction coefficient of the environment are altered.</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">article</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="a">Creative Commons Attribution</subfield>
    <subfield code="u">http://www.opendefinition.org/licenses/cc-by</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="a">Ada, Suzan Ece</subfield>
    <subfield code="u">Bogazici Univ, Dept Comp Engn, Istanbul, Turkey</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="z">md5:c915d426b64967b26b27e606525c4adc</subfield>
    <subfield code="s">138</subfield>
    <subfield code="u">https://aperta.ulakbim.gov.trrecord/253575/files/bib-0fc7802e-180e-4fea-8e4d-18fbf5ef348d.txt</subfield>
  </datafield>
  <controlfield tag="005">20230728192220.0</controlfield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2022-01-01</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1017/S0263574722000625</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Generalization in transfer learning: robust control of robot locomotion</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="4">
    <subfield code="v">40</subfield>
    <subfield code="p">ROBOTICA</subfield>
    <subfield code="c">3811-3836</subfield>
    <subfield code="n">11</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Ugur, Emre</subfield>
    <subfield code="u">Bogazici Univ, Dept Comp Engn, Istanbul, Turkey</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Akin, H. Levent</subfield>
    <subfield code="u">Bogazici Univ, Dept Comp Engn, Istanbul, Turkey</subfield>
  </datafield>
  <controlfield tag="001">253575</controlfield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-tubitak-destekli-proje-yayinlari</subfield>
  </datafield>
</record>