Skip to content

A DQN agent in Python that can solver the Lunar Lander problem from OpenAI

Notifications You must be signed in to change notification settings

anhducvu-bot/Q_Learning_LunarLander

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 

Repository files navigation

DQN agent that learn how to land the Lunar Lander on the Moon through trials and errors!

What?

  1. Environment: The RL agent will learn in the environment Lunar Lander by Open AI. Below is a small description of the environment:

"Landing pad is always at coordinates (0,0). Coordinates are the first two numbers in state vector. Reward for moving from the top of the screen to landing pad and zero speed is about 100..140 points. If lander moves away from landing pad it loses reward back. Episode finishes if the lander crashes or comes to rest, receiving additional -100 or +100 points. Each leg ground contact is +10. Firing main engine is -0.3 points each frame. Solved is 200 points. Landing outside landing pad is possible. Fuel is infinite, so an agent can learn to fly and then land on its first attempt. Four discrete actions available: do nothing, fire left orientation engine, fire main engine, fire right orientation engine."

More information about the environment can be found here

  1. The AI: The agent is a DQN agent that use cyclical learning rate.

How?

The model implemented is a vanilla DQN model with cyclical learning rate.

Performance:

Before Trainining: Click Here

After Training: Click Here

About

A DQN agent in Python that can solver the Lunar Lander problem from OpenAI

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages