/ddpg-lunar-lander

Implementation of the DDPG algorithm to safely land a lunar lander from Gymnasium environments

Primary LanguageJupyter NotebookMIT LicenseMIT

DDPG

Untrained Trained Actor

This repository contains an implementation of Deep Deterministic Policy Gradients (DDPG) which is a model-free reinforcement learning algorithm designed for continuous action spaces, utilizing an actor-critic architecture.

In ddpg.ipynb DDPG is implemented and well explained. It is then used to safely land a lunarlander from Gymnasium environments.