https://github.com/accraze/lunar-lander

Solving the OpenAI Gym "Lunar Lander v2" environment
https://github.com/accraze/lunar-lander

double-dqn openai-gym-solutions q-learning reinforcement-learning

Last synced: 7 months ago
JSON representation

Solving the OpenAI Gym "Lunar Lander v2" environment

• Host: GitHub
• URL: https://github.com/accraze/lunar-lander
• Owner: accraze
• Created: 2019-03-08T01:37:28.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2019-03-25T02:00:37.000Z (over 6 years ago)
• Last Synced: 2025-01-10T09:59:16.234Z (9 months ago)
• Topics: double-dqn, openai-gym-solutions, q-learning, reinforcement-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 916 KB
• Stars: 3
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# lunar lander

Solving the Lunar-Lander-v2 environment in the OpenAI Gym using a Double

Q-Learning Network.

![LunarLander Success](imgs/lunarlander.gif)

## install

```

pip install -r requirements.txt

```

## running

Check out the *ddqn.ipynb* notebook to see how to run the code