Date of Award

3-2019

Document Type

Thesis

Abstract

This paper discusses the results of using reinforcement learning to train an agent to play Mancala. I trained the agent by having it play a certain number of games against itself, and at the end of each game, I rewarded each move depending on whether it won or lost. Each move was rewarded by varying amounts based on how close to the end of the game it occurred. See game code at github.com/trb15a/mancala

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.