University group project concerning the implementation of an iterative learning controller tested on a Cart-Pole system. The code has been implemented in Matlab.

Disentangling Sources of Uncertainty for Active Exploration (Reinforcement Learning)

C# source code for simulation of the cart and pole balancing task.

Comparative study: Quantum vs. classical models for Cart Pole. Examining entanglement layers and data re-uploading, highlighting quantum model superiority.

A simple DQN implementation in Unity3D.

Cart pole balancing

first attempts on deep RL techniques

Using Genetic programming for sloving balancing double pendulum problem. The works demonstrates the difference of control performance by using non-Markov and Markov decision process

Modern applied deep learning with reinforcement methodology.

This project serves as an introduction to Deep Q-Learning and reinforcement learning concepts. The trained agent learns to balance the cart-pole system through iterative training and evaluation. You can modify the environment or parameters to further experiment with different reinforcement learning strategies.

Q Learning model for a cart-pole problem

Collection of examples for Reinforcement Learning

A simple fully connected network can be learned by genetic algorithm.

A real-time simulator of the cart-pole control system.

This repository contains a series of experiments and some theory related to reinforcement learning.

Matlab codes for learning Robotics

This is my implementation of Q-Learning on a cart-pole system using OpenAI Gym

Reinforcement Learning with Cart Pole Game