On the Use of Quantum Reinforcement Learning in Energy-Efficiency Scenarios

In the last few years, deep reinforcement learning has been proposed as a method to perform online in energy-efficiency scenarios such HVAC control, electric car energy management, or building just mention few. On other hand, quantum machine was born during decade extend classic level. this work, we propose study benefits and limitations of solve scenarios. As testbed, use existing energy-efficiency-based simulators compare algorithms with proposal. Results vehicle fuel consumption, profit optimization electrical charging stations applications suggest that neural networks are able problems better accuracy than their classical counterpart, obtaining cumulative reward fewer parameters be learned.