Undergraduate Dissertation (University of Malta) 2020-2023 - 'Autonomous Drone Control using Reinforcement Learning''

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.

Implementation of the Double Deep Q-Learning algorithm with a prioritized experience replay memory to train an agent to play the minichess variante Gardner Chess

Learning Mario Agent with the Double Deep Q-Learning Algorithm in the Gym Super Mario Environment.

Model-free, off-policy reinforcement learning with DQN's on Gym's environments

This project uses Deep Q-Learning to train a Mario agent in a reinforcement learning environment. The agent is optimized using dynamic exploration rates, custom reward shaping, and Prioritized Experience Replay to improve learning efficiency.

Play Super Mario Bros Game using Double Deep Q Network implemented in PyTorch.

Pytorch implementation of Double Deep Q Network (DDQN) learning with vectorized environments

This project is a Double Deep Q learning Agent that learns to play the dice game Yahtzee

Reinforcement learning implementation on C++

Double deep q network implementation in OpenAI Gym's "Mountain Car" environment