Reinforcement learning in a spiking neural network with memristive plasticity
2022 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA)(2022)
摘要
The reinforcement learning paradigm is for the first time presented for spiking neural network architecture with memristor-based local dynamic plasticity. The models of two kinds of such plasticity are used in the simulation study of the Cartpole task. Applying the Gaussian receptive field time-encoding scheme and simple reinforcing current pulses determined by the sign of reward change, the successful learning is demonstrated for both types of memristive plasticity.
更多查看译文
关键词
memristor,STDP,memristor-based plasticity,reinforcement learning,spiking neural network
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要