Skip to content

teaching an agent to play the Lunar Lander game from OpenAI Gym with REINFORCE algorithm

Notifications You must be signed in to change notification settings

EliottZemour/rl-lunarlander

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Project: Landing on the Moon

Presentation

Miniproject done in the framework of the CS-456 Artificial Neural Networks course at EPFL.
The goal was to teach an agent to play the Lunar Lander game from OpenAI Gym with REINFORCE algorithm. We investigated the effects of different baselines for the training of the agent.

image

How to use

The notebook can be opened on google colab, where the gym imports are taken care of.

About

teaching an agent to play the Lunar Lander game from OpenAI Gym with REINFORCE algorithm

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published