Deep QWOP Learning

Loading...

View/Download File

Wei-Wei Wu cum laude CSE fall2017.pdf (687.43 KB)

Persistent link to this item

https://hdl.handle.net/11299/194118

Statistics

View Statistics

Journal Title

Journal ISSN

Volume Title

Title

Deep QWOP Learning

Authors

Wu, Hung-Wei

Published Date

2017

Publisher

Type

Thesis or Dissertation

Abstract

We apply a deep learning model to the QWOP flash game, which requires control of a ragdoll athlete using only the keys “Q”, “W”, “O”, and “P”. The model is a convolutional neural network trained with Q-learning. By training the model with only raw pixel input, we show that our model is capable of successfully learning a control policy associated with playing QWOP. This model was successfully applied to a non-deterministic control environment in the form of a ragdoll physics flash game.

Keywords

College of Science and Engeineering

Computer Science

Cum Laude

Description

Related to

Replaces

License

Collections

Undergraduate Honors Theses

Series/Report Number

Funding information

Isbn identifier

Doi identifier

Previously Published Citation

Suggested citation

Wu, Hung-Wei. (2017). Deep QWOP Learning. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/194118.

Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.