Skip to content

Comparative study: Quantum vs. classical models for Cart Pole. Examining entanglement layers and data re-uploading, highlighting quantum model superiority.

Notifications You must be signed in to change notification settings

mcpeixoto/ReinforcementQML

Repository files navigation

Quantum Reinforcement Learning to Solve Cart Pole Environment

Done for the class of Quantum Data Science, University of Minho

Masters in Physics Engineering - Information Physics Branch - 2022/23

Abstract

We conducted a comprehensive investigation into the application of quantum reinforcement learning for solving the Cart Pole environment, comparing it with a classical model based on deep neural networks. Our study explored various quantum models, examining the impact of different entanglement layer configurations and the utilization of data re-uploading. Additionally, we varied the number of layers in the deep neural network.

Our findings indicate that, for models with fewer than four layers, the classical model demonstrates compatibility with the quantum model. However, as the number of layers increases, the quantum model outperforms the classical one. Remarkably, the quantum model exhibited the best performance during both training and testing stages.

Overall, our study highlights the advantages of employing quantum reinforcement learning for the Cart Pole environment, showcasing the superiority of certain quantum models over classical counterparts.

Files

About

Comparative study: Quantum vs. classical models for Cart Pole. Examining entanglement layers and data re-uploading, highlighting quantum model superiority.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published