Deep Reinforcement Learning with Spiking Q-learning.
Ding ChenPeixi PengTiejun HuangYonghong TianPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- action selection
- basal ganglia
- reinforcement learning algorithms
- state space
- optimal policy
- model free
- bio inspired
- reinforcement learning methods
- temporal difference
- multi agent reinforcement learning
- feed forward
- learning algorithm
- stochastic approximation
- temporal difference learning
- multi agent
- state action space
- markov decision processes
- cooperative
- dynamic programming
- state action
- function approximators
- control problems
- continuous state and action spaces
- learning rules
- continuous state
- neural network
- single neuron
- neuron model
- learning agents
- mobile robot
- rl algorithms
- continuous state spaces
- spiking neurons
- swarm intelligence