Markov Decision Process and Temporal Difference algorithms
-
Updated
Mar 14, 2021 - C#
Markov Decision Process and Temporal Difference algorithms
An agent learns the optimal path towards its goal from any starting point while avoiding obstacles.
This project is a C# implementation of the popular game "Frozen Lake" and an AI agent that can play the game using the Q-learning algorithm. The game consists of a grid of tiles, some of which are safe to walk on, while others will cause the player to receive damage.
A Markov model builder and simulator
An rougelike board game where you create the dungeon + environmental conditions and an AI agent will determine the optimal policy to traverse the dungeon to the treasure.
Add a description, image, and links to the markov-decision-processes topic page so that developers can more easily learn about it.
To associate your repository with the markov-decision-processes topic, visit your repo's landing page and select "manage topics."