A visualization tool for policy iteration and value iteration
-
Updated
Feb 28, 2021 - JavaScript
A visualization tool for policy iteration and value iteration
Personal implementation in C++ of http://www.cs.put.poznan.pl/mszubert/pub/szubert2014cig.pdf. Results could be reproduced. It's an algorithm that learns by itself to solve the 2048 game. It doesn't use deep learning (aka. neural networks). But it learns by itself using the Bellman equations.
Add a description, image, and links to the bellman-equation topic page so that developers can more easily learn about it.
To associate your repository with the bellman-equation topic, visit your repo's landing page and select "manage topics."