Skip to content
/ 2048-DeepQLearning Public

Implementation of an agent able to play 2048. Report, evaluation and implementation details in the GitHub repository. During the project I gained experience with Reinforcement learning technologies such as the gym framework and the Keras-rl library.

1 star 2 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

andreamagnante/2048-DeepQLearning

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
DQN_2048
DQN_2048
 
 
NN_2048
NN_2048
 
 
imagesEvaluation
imagesEvaluation
 
 
2048.gif
2048.gif
 
 
ML_2048_report.pdf
ML_2048_report.pdf
 
 
README.md
README.md
 
 
evaluation.pdf
evaluation.pdf
 
 

Repository files navigation

2048 A Deep Q-Learning-Approach

Project for the Machine Learning course - La Sapienza Università di Roma

Implementing an agent for the 2048 game using a reinforcement learning approach.

For more details look at: ML_2048_report.pdf

Let's see in action: https://youtu.be/swc_otVJJrA

Requirements

  • tensorflow==1.14.0
  • keras-rl
  • keras==2.2.0
  • gym
  • matplotlib
  • pandas
  • numpy

Graphic Interface: visualize=True in test/fit

Evaluation:

Training results with 5 millions steps

alt text

Dataframe training results with 5.000 steps

alt text

Dataframe training results with 5.000.000 steps

alt text

About

Implementation of an agent able to play 2048. Report, evaluation and implementation details in the GitHub repository. During the project I gained experience with Reinforcement learning technologies such as the gym framework and the Keras-rl library.

Topics

machine-learning ml 2048 2048-game

Resources

Readme
Activity

Stars

1 star

Watchers

2 watching

Forks

2 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages