5,400,485 AI resources indexedWorking toward the world’s largest AI resource index.

Lunar Lander

A physics benchmark for bringing a lander to a target with discrete thrust commands.

Published by Farama Foundation

PDF
No ratings yet

Setup and evaluation

Evaluate how a policy balances descent speed, alignment, and fuel use. Record successful landings and mean return across fixed seeds, with the same wind setting in every run.

Install with pip install "gymnasium[box2d]" and create the environment with gymnasium.make('LunarLander-v3').

Framework
Gymnasium
Access
Local Gymnasium environment. No account required.
Official setup and documentation