Murilo Saraiva de Queiroza, Roberto Coelho de Berredob, and Antonio de Padua Bragab (2006) "Reinforcement learning of a simple control task using the spike response model." Neurocomputing, Volume 70, Issues 1-3, December 2006, Pages 14-20 (Neural Networks - Selected Papers from the 7th Brazilian Symposium on Neural Networks (SBRN '04), 7th Brazilian Symposium on Neural Networks) rate model (little or no resemblance to biological neurons. integrate-and-fire model --- generalization ---> spiking responce model ===== [17] Direct-gradient-based-reinforcement-learning, [12] Hebbian-synaptic-modifications-in-spiking-neurons-that-learn hebbian synaptic update rule for reinforcement learning -------------------------------------------------------------------------------- Bartlett Baxter Technical-report Australian-National-University (November 1999). Subject: paper: hebbian synaptic update rule for reinforcement learning From: Peter Date: Sat, 27 Nov 1999 13:17:58 +1100 Organization: Australian National University Reply-to: Peter.Bartlett@anu.edu.au Sender: Peter.Bartlett@syseng.anu.edu.au [14][15] Direct-gradient-based-reinforcement-learning : I. gradient estimation algorithms, Unsupervised-clustering-with-spiking-neurons-by-sparse-temporal-coding-and-multilayer-RBF-networks 3 papers by google with spiking-neuron grid-woerld