Demo project using tabular Q-learning algorithm

Multi-Agent Car Parking using Reinforcement Learning.

Simple Example of the Q Learning Algorithm

Reinforcement Learning Experiments in C#

Maze solving game using agent driven by Q dictionary. Agent must take the most apples and avoid mines.

Autos virtuales conducidos mediante algoritmos genéticos, redes neuronales y otra implementación de Q-learning construido en el motor grafico Unity2D.

An agent learns the optimal path towards its goal from any starting point while avoiding obstacles.

Data Science University project for implementing a Q-Learning and Reinforcement Learning to the TicTacToe game.

Dissertation project: Combining Behaviour Trees and Reinforcement Learning for Game AI

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.

Q-Learning written in C#. Made with Unity.

Reinforcement Learning excercise where the agent is in a maze looking to find a square containing gold

A pathfinding project that uses Q-Learning, a reinforcement learning algorithm, where an agent learns to navigate to a goal through iterative exploration, with reaching the goal as its only reward.

A WPF application that allows you to train and play against a neural network in a game of TicTacToe