Quantum gated recurrent neural networks for continuous dynamic temporal decision-making
Performance breakthroughs in dynamic temporal decision-making tasks have long been a core research objective in reinforcement learning. Yet traditional policy networks, including long short-term memory (LSTM) networks, gated recurrent unit (GRU) and feedforward neural network (FNN), have long been hampered by inherent...
JiaZhao Shen, Zijun Guo, Weizhen Ding et al.
· Physica Scripta · 0 citations