Learning from Delayed Reward und Punishment in a Spiking Neural Network Model of Basal Ganglia with Opposing D1/D2 Plasticity.
Jenia JitsevNobi AbrahamAbigail MorrisonMarc TittgemeyerPublished in: ICANN (1) (2012)
Keyphrases
- neural network model
- basal ganglia
- action selection
- reinforcement learning
- learning algorithm
- learning rules
- neural network
- artificial neural networks
- feed forward
- rbf neural network
- high dimensional
- learning mechanism
- biologically plausible
- spiking neural networks
- computational model
- radial basis function
- network architecture