Tabular methods for reinforcement learning

path planning using Q learning algorithm

The following project concerns the development of an intelligent agent for the famous game produced by Nintendo Super Mario Bros. More in detail: the goal of this project was to design, implement and train an agent with the Q-learning reinforcement learning algorithm.

Demonstration of Q-Learning and SARSA algorithms utilizing Python and OpenAI GYM

This github contains a simple OpenAi Gym Maze Enviroment and (at now) a RL Algorithm to solve it.

Reinforcement learning algorithm implements.

Solutions for OpenAI Gym RL environments

Applying PBT optimization technique to different domains

Using the SARSA to beat the environment, Windy Gridworld. Implement in C++.

Implementation of certain crucial algorithms in the field of reinforcement learning.

Implementation of SARSA algorithm for path planning

The implementation of some reinforcement learning techniques like (Q-learning, SARSA, DQN) in two assignments and one big project.

Reinforcement learning system using the SARSA-RL Algorithm to learn to play a simple physics game, referred to as the The Acrobat Game

Reinforcement Learning Project for Artificial Intelligence for Robotics course at the University of Genoa.

Implementing Reinforcement Learning (RL) Algorithms for global path planning in tasks of mobile robot navigation.

Optimal Placement of VNFs using Genetic & Tabu Search Algorithms and Service Function Chaining using Q-Learning & SARSA Algorithms in an Multi-Access Edge Computing Environment

Pac-Man RL Agent

Two reinforcement learning algorithms (Standard SARSA Control and Tabular Dyna-Q) where an agent learns to traverse a randomly generated maze

Ludo-RL è un progetto che ha visto lo sviluppo e l'implementazione di un sistema di apprendimento per rinforzo finalizzato al gioco da tavolo Ludo.

Temporal Difference methods - A simple implementation of SARSA algorithm applied to OpenAI gym's "CliffWalking" environment.