Model-based reinforcement learning with spiking neurons

@inproceedings{Friedrich2014ModelbasedRL,
  title={Model-based reinforcement learning with spiking neurons},
  author={Johannes Friedrich and M{\'a}t{\'e} Lengyel},
  year={2014}
}
Behavioural and neuroscientific data on reward-based decision making point to a fundamental distinction between habitual and goal-directed action selection. An increasingly explicit set of neuroscientific ideas has been established for habit formation, whereas goal-directed control has only recently started to attract researchers’ attention. While using functional magnetic resonance imaging to address the involvement of brain areas in goal-directed control abounds, ideas on its algorithmic and… CONTINUE READING