Cart pole

[vc_row][vc_column][vc_column_text]

Cart Pole experiment

This experiment uses Tensorflow.js in order to solve the cartpole problem using Policy Gradient Reinforcement learning.

  • The Source code is available on Github
  • Try the experiment in your browser

Algorithms

You can choose between several algorithms :

  • REINFORCE
  • REINFORCE with baseline
  • Actor Critic (A2C)

Technologies

  • Tensorflow.js is used for the neural network
  • The Experiment is rendered using Phaser 3 game engine
  • Tfjs-vis is used for learning graph visualization

 [/vc_column_text][/vc_column][/vc_row][vc_row][vc_column][vc_single_image image=”554″ img_size=”full” alignment=”center”][/vc_column][/vc_row][vc_row][vc_column][vc_column_text]The Settings page allows to:

  • Configure the Hypermarameters of the Policy and Value models
  • Store the trained models in the Browser
  • Retrieve and use stored models

[/vc_column_text][vc_single_image image=”646″ img_size=”full” alignment=”center”][/vc_column][/vc_row][vc_row][vc_column][vc_video link=”https://www.youtube.com/watch?v=q8lftqQH7O8&”][/vc_column][/vc_row]

Back To Top
Theme Mode