reinforcement learning algorithms from the book by Sutton and Barto

sokoban game solver through Multiple Search Algorithms and Reinforcement Learning (Q-Learning)

Implementation of Q-Learning Algorithm

Q-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It does not require a model of the environment (hence "model-free"), and it can handle problems with stochastic transitions and rewards without requiring adaptations.

Sokoban AI Solver (HKUST COMP3211 Project)

A tic tac toe game in java, which can be trained by machine learning (console & gui).

QLearning algorithm of Reinforcement Learning implemented in the GVGAI platform to solve the 111st game, called Arkanoid.

A series of experiments on the performance of Q-Learning Agents in the Dots and Boxes game.

This contains the most commonly used machine learning and deep learning models written from scratch without the use if any libraries except Numpy which is used for calculations

Qlearning Blackjack/Stock market analyst AI

FrozenLake - OpenAI's exercise resolved with Q-learning algorithm

Implementation de l'algorithme QLearning en JAVA

Proyecto básico aplicando el algoritmo Qlearning para crear un agente que resuelva el juego 15 de la plataforma GVGAI. Implementado en JAVA.

Reinforcement learning agent learning to navigate an environment containing rewards and punishments.

用QLearning增强学习算法玩拼图游戏

QLearning implementation reinforced by norms in a multi-agent simulation

Golf game using Q-learning, A* pathfinding and bruteforce with a Runge-Kutta physics solver in Java

IASA (Artificial Intelligence of Autonomous Systems) class projects and resources of LEIM course at ISEL