Automating Pacman with Deep Q-Learning Using PYgame

DOI

No DOI

Published In

Volume 3, Issue 3 (2022)

Published Online

May-June 2022

Pages

437-439

Article Type

Research Article

Check for updates

No DOI available for cross-reference

Abstract: A computer program capable of doing a human-level performance on a number of games. Just like a human, the algorithm played based on its vision of the screen. Starting from scratch, it discovered gameplay strategies that let it meet (and in many cases, exceed) human benchmarks. In the years since researchers have made a number of improvements that super-charge performance and solve games faster than ever before. We've been working to implement these advancements in Keras — the open-source, highly accessible machine learning framework— and in this post, we'll walk through the details of how they work and how they can be used to master Ms. Pac-man.