jatinror/lunar-lander-dqn

DQN LunarLander-v2 Agent

This model was trained using Deep Q-Network (DQN) from Stable-Baselines3 on the LunarLander-v2 environment.

Environment

• Name: LunarLander-v2
• Observation Space: 8-dimensional continuous state
• Action Space: 4 discrete actions

Algorithm

• DQN (Deep Q-Network)
• Library: Stable-Baselines3

Model File

The trained model is saved as:

model.zip

How to Load the Model

from stable_baselines3 import DQN

model = DQN.load("model")