A spiking neural network model of model-free reinforcement learning (Nakano et al 2015)

"Spiking neural networks provide a theoretically grounded means to test computational hypotheses on neurally plausible algorithms of reinforcement learning through numerical simulation. ... In this work, we use a spiking neural network model to approximate the free energy of a restricted Boltzmann machine and apply it to the solution of PORL (partially observable reinforcement learning) problems with high-dimensional observations. ... The way spiking neural networks handle PORL problems may provide a glimpse into the underlying laws of neural information processing which can only be discovered through such a top-down approach. "

Model Type: Realistic Network

Cell Type(s): Abstract integrate-and-fire leaky neuron

Model Concept(s): Reinforcement Learning

Simulation Environment: NEST

Implementer(s): Nakano, Takashi [nakano.takashi at gmail.com]

References:

Nakano T, Otsuka M, Yoshimoto J, Doya K. (2015). A spiking neural network model of model-free reinforcement learning with high-dimensional sensory input and perceptual ambiguity. PloS one. 10 [PubMed]