%0 Journal Article
%T Reinforcement Learning with Deep Quantum Neural Networks
%A Wei Hu
%A James Hu
%J Journal of Quantum Information Science
%P 1-14
%@ 2162-576X
%D 2019
%I Scientific Research Publishing
%R 10.4236/jqis.2019.91001
%X The advantage of quantum computers
over classical computers fuels the recent trend of developing machine learning
algorithms on quantum computers, which can potentially lead to breakthroughs
and new learning models in this area. The aim of our study is to explore deep
quantum reinforcement learning (RL) on photonic quantum computers, which can
process information stored in the quantum states of light. These quantum
computers can naturally represent continuous variables, making them an ideal platform to create quantum
versions of neural networks. Using quantum photonic circuits, we implement Q
learning and actor-critic algorithms with multilayer quantum neural networks and
test them in the grid world environment. Our experiments show that 1) these
quantum algorithms can solve the RL problem and 2) compared to one layer, using
three layer quantum networks improves the learning of both algorithms in terms
of rewards collected. In summary, our findings suggest that having more layers
in deep quantum RL can enhance the learning outcome.
%K Continuous-Variable Quantum Computers
%K Quantum Machine Learning
%K Quantum Reinforcement Learning
%K Deep Learning
%K Q Learning
%K Actor-Critic
%K Grid World Environment
%U http://www.scirp.org/journal/PaperInformation.aspx?PaperID=90994