Distilling Neuron Spike with High Temperature in Reinforcement Learning Agents.
Ling ZhangJian CaoYuan ZhangBohan ZhouShuo FengPublished in: CoRR (2021)
Keyphrases
- high temperature
- reinforcement learning agents
- spike trains
- spiking neurons
- dynamic environments
- hodgkin huxley
- reinforcement learning
- synaptic weights
- state abstraction
- transfer learning
- neural network
- learning algorithm
- multi agent
- biologically plausible
- multi agent environments
- machine learning
- mobile robot
- silicon dioxide
- reinforcement learning methods
- prior knowledge
- cooperative