Reinforcement learning algorithms in 2x2 matrix games

Loading...

Sign in or sign up now!
Alert icon
Upgrade to the latest Flash Player for improved playback performance. Upgrade now or more info.
810 views
Loading...
Alert icon
Sign in or sign up now!
Alert icon

Uploaded by on Apr 27, 2010

This video illustrates the learning behavior of different variations of two algorithms (FALA and Q-learning) in three games: Prisoners' Dilemma (FALA, Q-learning), Matching Pennies (FALA, Lenient Q-learning), Battle of the Sexes (FALA, Q-learning).

  • likes, 0 dislikes

Link to this comment:

Share to:

Uploader Comments (MichaelKaisers)

  • Awesome. How were the visuals created?

  • @rhaikh Simulations were performed in Matlab.

see all

All Comments (3)

Sign In or Sign Up now to post a comment!
  • can you post the code please..

Loading...

Alert icon
0 / 00Unsaved Playlist Return to active list
    1. Your queue is empty. Add videos to your queue using this button:
      or sign in to load a different list.
    Loading...Loading...Saving...
    • Clear all videos from this list
    • Learn more