File:Q Learning Simple Movement Two Target.gif

From UBC Wiki

Q_Learning_Simple_Movement_Two_Target.gif(512 × 386 pixels, file size: 6.01 MB, MIME type: image/gif, looped, 594 frames, 20 s)

Note: Due to technical limitations, thumbnails of high resolution GIF images such as this one will not be animated.

Summary

Description
English: Training an AI agent with Q Learning, then observing the resulting policy. Agent is rewarded for reaching one of two goals - the goal "containing" the reward is chosen at random with a 50/50 chance, so the agent first visits the closest goal before continuing on to the second if no reward is presented. Grid colors indicate the expected future reward as discovered by Q Learning.
Date 16 April 2018(2018-04-16) (purge)
File source Own Work
Author Alistair Wick

Licensing

I, the copyright holder of this work, hereby publish it under the following license:
Some rights reserved
Permission is granted to copy, distribute and/or modify this document according to the terms in Creative Commons License, Attribution-ShareAlike 3.0. The full text of this license may be found here: CC by-sa 3.0
Attribution-Share-a-like

File history

Click on a date/time to view the file as it appeared at that time.

Date/TimeThumbnailDimensionsUserComment
current21:54, 16 April 2018Thumbnail for version as of 21:54, 16 April 2018512 × 386 (6.01 MB)AlistairWick (talk | contribs)
21:48, 16 April 2018Thumbnail for version as of 21:48, 16 April 2018512 × 386 (14.14 MB)AlistairWick (talk | contribs)
20:58, 16 April 2018Thumbnail for version as of 20:58, 16 April 2018512 × 386 (14.14 MB)AlistairWick (talk | contribs)User created page with UploadWizard

The following page uses this file: