IEEE - Institute of Electrical and Electronics Engineers, Inc. - Hardware-Friendly Actor-Critic Reinforcement Learning Through Modulation of Spike-Timing-Dependent Plasticity

Author(s): Nan Zheng ; Pinaki Mazumder
Sponsor(s): IEEE Comput. Soc. Tech. Committee on Distributed Process
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 February 2017
Volume: 66
Page(s): 299 - 311
ISSN (Paper): 0018-9340
DOI: 10.1109/TC.2016.2595580
Regular:

In this work, we propose a hardware-friendly reinforcement learning algorithm. The learning algorithm is based on an actor-critic structure implemented with spiking neural networks (SNNs). A... View More

Advertisement