% 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”.

@INPROCEEDINGS{Jitsev:141532,
      author       = {Jitsev, Jenia and Abraham, Nobi and Tittgemeyer, Marc and
                      Morrison, Abigail},
      title        = {{F}unctional role of opponent, dopamine modulated {D}1/{D}2
                      plasticity in prediction error-driven reinforcement learning
                      in the basal ganglia},
      reportid     = {FZJ-2013-06700},
      year         = {2013},
      abstract     = {In this work, we introduce a spiking actor-critic network
                      model of learning from both reward and punishment in the
                      basal ganglia. Both the dorsal (actor) and ventral (critic)
                      striatum are assumed to contain populations of D1 and D2
                      medium spiny neurons (MSNs). In the ventral striatum, this
                      allows separate representation of both positive and negative
                      expected outcomes by respective D1/D2 MSN populations, which
                      we hypothesize to reside in the shell part of the Nucleus
                      Accumbens. The positive and negative outcome expectations
                      are fed to dopamine (DA) neurons in VTA region, which
                      compute and signal total prediction error by DA release.
                      Based on recent experimental work [1], DA level is assumed
                      to modulate plasticity of D1 and D2 synapses in opposing
                      way, inducing LTP on D1 and LTD on D2 synapses if being high
                      and vice versa if being low. Crucially, this form of
                      opponent plasticity implements temporal-difference (TD)-like
                      update of both positive and negative outcome expectations
                      and performs appropriate adaptation of action preferences.We
                      implemented the network in the NEST simulator [2] using
                      leaky integrate-and-fire spiking neurons, and designed a
                      battery of experiments in various grid world tasks. Across
                      the tasks the network can learn both to approach the delayed
                      rewards while consequently avoiding punishments, which posed
                      severe difficulties for the previous model without D1/D2
                      segregation [3]. The model highlights thus the functional
                      role of D1/D2 MSN segregation within the striatum in
                      implementing appropriate TD-like learning from both reward
                      and punishment and explains necessity for opponent direction
                      of DA-dependent plasticity found at synapses converging on
                      distinct striatal MSN types. The approach can be further
                      extended to study how abnormal D1/D2 plasticity may lead to
                      a reorganization of the basal ganglia network towards
                      pathological, dysfunctional states, like for instance those
                      observed in Parkinson disease under condition of progressive
                      dopamine depletion.[1] Shen, W., Flajolet, M., Greengard, P.
                      and Surmeier, D. J. Dichotomous dopaminergic control of
                      striatal synaptic plasticity. Science, 2008, 321, 848-851[2]
                      Gewaltig M-O and Diesmann M (2007). NEST, Scholarpedia
                      2(4):1430[3] Potjans, W., Diesmann, M. and Morrison, A. An
                      imperfect dopaminergic error signal can drive
                      temporal-difference learning. PLoS Comput. Biol., 2011, 7},
      month         = {Oct},
      date          = {2013-10-22},
      organization  = {Computational Psychiatry 2013, Miami
                       (USA), 22 Oct 2013 - 23 Oct 2013},
      subtyp        = {Other},
      cin          = {INM-6 / IAS-6},
      cid          = {I:(DE-Juel1)INM-6-20090406 / I:(DE-Juel1)IAS-6-20130828},
      pnm          = {311 - Signaling pathways, cell and tumor biology (POF2-311)
                      / HASB - Helmholtz Alliance on Systems Biology
                      (HGF-SystemsBiology) / SMHB - Supercomputing and Modelling
                      for the Human Brain (HGF-SMHB-2013-2017) / W2Morrison -
                      W2/W3 Professorinnen Programm der Helmholtzgemeinschaft
                      (B1175.01.12)},
      pid          = {G:(DE-HGF)POF2-311 / G:(DE-Juel1)HGF-SystemsBiology /
                      G:(DE-Juel1)HGF-SMHB-2013-2017 / G:(DE-HGF)B1175.01.12},
      typ          = {PUB:(DE-HGF)24},
      url          = {https://juser.fz-juelich.de/record/141532},
}