/Lunar_Lander

This repository showcases Deep Q-Learning for Lunar Lander training, . The project includes Q-Network architecture, experience replay, and network weight updates. Explore the code and watch a video of the trained agent in action.

Primary LanguageJupyter Notebook

Deep Q-Learning - Lunar Lander

This repository contains an implementation of the Deep Q-Learning algorithm to solve the Lunar Lander environment from OpenAI Gym. The goal is to train an agent to land a spacecraft on a designated landing pad by applying appropriate force and adjusting the spacecraft's orientation.

Overview

The Deep Q-Learning algorithm is a reinforcement learning technique that combines Q-Learning with deep neural networks to approximate the action-value function. This allows the agent to learn an optimal policy for selecting actions in complex environments with high-dimensional state spaces.

Requirements

  • Python 3.x
  • TensorFlow
  • OpenAI Gym
  • NumPy
  • Pillow
  • pyvirtualdisplay

Usage

  1. Clone the repository:
git clone https://github.com/your-repo/deep-q-learning-lunar-lander.git