Reinforcement learning with a network of spiking agents

Sep 11, 2019 NeurIPS 2019 Workshop Neuro AI Blind Submission readers: everyone
  • Keywords: Reinforcement learning, multi-agent learning, spiking neurons
  • Abstract: 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 (Schultz et al.). 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 modulates its firing policy based on local information and a global prediction error, can learn complex action representations to solve RL tasks. We further show how leveraging principles of modularity and population coding inspired from the brain can help reduce variance in the learning updates making it a viable optimization technique.
0 Replies

Loading