Learning to land
DQN and PPO agents learn controlled spacecraft landings in Gymnasium's LunarLander-v3.
Agent replay
Recorded agents
How it works.
Observe the state
The agent receives lander position, velocity, angle, and ground-contact observations.
From the original project.
Saved artifacts · click to inspect
Original artifact ↗
Original artifact ↗
Continue in the source.
Open the source notebook in Jupyter, Colab, or the environment described in the README. Data and model downloads may be required.
git clone https://github.com/eforus-overseer/LunarLander-DQN-vs-PPO.gitProject artifacts.
notebooks/lunar_lander_dqn_v1.ipynb ↗notebooks/lunar_lander_dqn_v1.py ↗notebooks/lunar_lander_dqn_v2.py ↗
Source links point to the original public repository. Credit belongs to the project authors and the dependencies credited there.