Spike-Based Reinforcement Learning in Continuous State and Action Space: When Policy Gradient Methods Fail

• Eleni Vasilaki ,

  * E-mail: E.Vasilaki@sheffield.ac.uk

  Affiliations Laboratory of Computational Neuroscience, EPFL, Lausanne, Switzerland, Department of Computer Science, University of Sheffield, Sheffield, United Kingdom

  ⨯
• Nicolas Frémaux,

  Affiliation Laboratory of Computational Neuroscience, EPFL, Lausanne, Switzerland

  ⨯
• Robert Urbanczik,

  Affiliation Department of Physiology, University of Bern, Bern, Switzerland

  ⨯
• Walter Senn,

  Affiliation Department of Physiology, University of Bern, Bern, Switzerland

  ⨯
• Wulfram Gerstner

  Affiliation Laboratory of Computational Neuroscience, EPFL, Lausanne, Switzerland

  ⨯