MarioPPO implementation uses the TensorFlow machine learning platform

This code repository contains the implementation of Q-Learning agent for Mountain Car game. It is part of the lab exercise for the COSC-604 Artificial Intelligence course for masters students at Khalifa University.

Using a Deep Q Network(DQN) to play Atari Breakout

PPO, TD3

Snake game reinforcement learning

A simple implementation of the Proximal Policy Optimization (PPO) algorithm using Pytorch.

Deep Reinforcement Learning based Rubik’s Cube solver written in JAX, Haiku and RLax. Developed a custom environment supporting cubes of variable size. Currently developing support for DQN, QR-DQN and PPO.

Reinforcement Learning using OpenAI Gym MountainCar Environment

Try out various methods of Reinforcement Learning to automate SnakeGame

Self Training Sneak Game with Reinforcement Learning

[ ❌ Deprecated] A reinforcement learning environment, in which the agent learns to navigate and drive a car (ackermann steering) to a goal position.

Classic RL control algorithm implementations found in Sutton and Barto book.

Intro to Reinforcement Learning

Bomberman agent using reinforcement learning

Reinforcement Learning Using OpenAI Gym

Repository of Reinforcement Learning projects done during the course @sapienza

Reinforcement Learning (COMP 579) Course Project

Implementations of common (vanilla) reinforcement learning algorithms from Sutton & Barto.

Python implementation of the Q Learning algorithm with the DDQN trick on OpenAI's version of the cart-pole problem