LunarLander-DQN is a Python project that implements a Deep Q-Network (DQN) algorithm with extension for training an agent to land a lunar lander spacecraft. It utilizes the Gymnasium library for the environment simulation and Stable Baselines3 for reinforcement learning. With the power of PyTorch, it provides efficient training and evaluation of the agent. The project aims to achieve high-performance lunar lander control through deep reinforcement learning techniques.
- create unit tests for the code
- model loading, reloading, saving
- generation of video where agent is playing the game
- Rainbow DQN