% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Jordan:863864,
      author       = {Jordan, Jakob and Weidel, Philipp and Morrison, Abigail},
      title        = {{A} closed-loop toolchain for neural network simulations of
                      learning autonomous agents},
      journal      = {Frontiers in computational neuroscience},
      volume       = {13},
      issn         = {1662-5188},
      address      = {Lausanne},
      publisher    = {Frontiers Research Foundation},
      reportid     = {FZJ-2019-03835},
      pages        = {46},
      year         = {2019},
      abstract     = {Neural network simulation is an important tool for
                      generating and evaluating hypotheses on the structure,
                      dynamics and function of neural circuits. For scientific
                      questions addressing organisms operating autonomously in
                      their environments, in particular where learning is
                      involved, it is crucial to be able to operate such
                      simulations in a closed-loop fashion. In such a set-up, the
                      neural agent continuously receives sensory stimuli from the
                      environment and provides motor signals that manipulate the
                      environment or move the agent within it. So far, most
                      studies requiring such functionality have been conducted
                      with custom simulation scripts and manually implemented
                      tasks. This makes it difficult for other researchers to
                      reproduce and build upon previous work and nearly impossible
                      to compare the performance of different learning
                      architectures. In this work, we present a novel approach to
                      solve this problem, connecting benchmark tools from the
                      field of machine learning and state-of-the-art neural
                      network simulators from computational neuroscience. The
                      resulting toolchain enables researchers in both fields to
                      make use of well-tested high-performance simulation software
                      supporting biologically plausible neuron, synapse and
                      network models and allows them to evaluate and compare their
                      approach on the basis of standardized environments with
                      various levels of complexity. We demonstrate the
                      functionality of the toolchain by implementing a neuronal
                      actor-critic architecture for reinforcement learning in the
                      NEST simulator and successfully training it on two different
                      environments from the OpenAI Gym. We compare its performance
                      to a previously suggested neural network model of
                      reinforcement learning in the basal ganglia and a generic
                      Q-learning algorithm.},
      cin          = {INM-6 / IAS-6 / INM-10},
      ddc          = {610},
      cid          = {I:(DE-Juel1)INM-6-20090406 / I:(DE-Juel1)IAS-6-20130828 /
                      I:(DE-Juel1)INM-10-20170113},
      pnm          = {574 - Theory, modelling and simulation (POF3-574) /
                      RL-BRD-J - Neural network mechanisms of reinforcement
                      learning (BMBF-01GQ1343) / W2Morrison - W2/W3 Professorinnen
                      Programm der Helmholtzgemeinschaft (B1175.01.12) / SMHB -
                      Supercomputing and Modelling for the Human Brain
                      (HGF-SMHB-2013-2017) / HBP SGA2 - Human Brain Project
                      Specific Grant Agreement 2 (785907) / HBP SGA1 - Human Brain
                      Project Specific Grant Agreement 1 (720270)},
      pid          = {G:(DE-HGF)POF3-574 / G:(DE-Juel1)BMBF-01GQ1343 /
                      G:(DE-HGF)B1175.01.12 / G:(DE-Juel1)HGF-SMHB-2013-2017 /
                      G:(EU-Grant)785907 / G:(EU-Grant)720270},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:31427939},
      UT           = {WOS:000478905500001},
      doi          = {10.3389/fncom.2019.00046},
      url          = {https://juser.fz-juelich.de/record/863864},
}