Corpus ID: 204780868

Reinforcement learning with a network of spiking agents

@article{Aenugu2019ReinforcementLW,
  title={Reinforcement learning with a network of spiking agents},
  author={Sneha Aenugu and Abhishek Sharma and Sasikiran Yelamarthi and Hananel Hazan and P. S. Thomas and R. Kozma},
  journal={arXiv: Learning},
  year={2019}
}
Neuroscientific theory suggests that dopaminergic neurons broadcast global reward prediction errors to large areas of the brain influencing the synaptic plasticity of the neurons in those regions. We build on this theory to propose a multi-agent learning framework with spiking neurons in the generalized linear model (GLM) formulation as agents, to solve reinforcement learning (RL) tasks. We show that a network of GLM spiking agents connected in a hierarchical fashion, where each spiking agent… Expand

Figures from this paper

Reinforcement Learning with Feedback-modulated TD-STDP

References

SHOWING 1-10 OF 19 REFERENCES
Learning in Spiking Neural Networks by Reinforcement of Stochastic Synaptic Transmission
Human-level control through deep reinforcement learning
Neuronal coding of prediction errors.
Reinforcement Learning: An Introduction
Simple statistical gradient-following algorithms for connectionist reinforcement learning
Spatio-temporal correlations and visual signalling in a complete neuronal population
Noisy Spiking Neurons with Temporal Coding have more Computational Power than Sigmoidal Neurons
...
1
2
...