Spiking Reinforcement Learning with Memory Ability for Mapless Navigation.
Bo YangMengwen YuanChengjun ZhangChaofei HongGang PanHuajin TangPublished in: IROS (2023)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- neuron model
- basal ganglia
- feed forward
- data sets
- computing power
- random access
- action selection
- temporal difference
- reinforcement learning algorithms
- computational power
- robotic control
- model free
- memory requirements
- markov decision processes
- multi agent
- machine learning