Alert icon
We're changing our privacy policy. This stuff matters.  Learn more  Dismiss

First Experiments with Policy Gradient Learning on a real robot

Loading...

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

Uploaded by on Sep 29, 2009

This the first successfull experiment of my master thesis. The Robot learns the Parameters of a PD-Controller, which trys to minimize the distance to the ball in about 30 Trials. It uses the episodic natural actor critic algorithm with a constant baseline to compute the policy gradient.

Category:

Science & Technology

Tags:

License:

Standard YouTube License

  • likes, 0 dislikes

Link to this comment:

Share to:
see all

All Comments (0)

Sign In or Sign Up now to post a comment!
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