Reinforcement Learning
author: Satinder Singh,
Electrical Engineering and Computer Science Department, University of Michigan
published: Feb. 25, 2007, recorded: February 2006, views: 29106
published: Feb. 25, 2007, recorded: February 2006, views: 29106
Slides
Related content
Report a problem or upload files
If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Watch videos: (click on thumbnail to launch)
Part 1 59:43
Part 2 55:55
Part 3 55:18
Part 4 39:25
Part 5 59:48
Part 6 28:48
Description
MDPs/VI,
Q learning (w/ proof),
TD(lambda),
Function approximation,
options,
PSRs
Download slides:
Link this page
Would you like to put a link to this lecture on your homepage?Go ahead! Copy the HTML snippet !
Reviews and comments:
I can't seem to find the download URL. Streaming will not work for me, as I need to view these in a place where the network is not available. Is there a download link somewhere? Thanks.
By rewarding itself for correct actions, or punishing itself for incorrect ones, it can learn over time which actions lead to good outcomes and which do not. Reinforcement learning does not require any pre-determined rules like other forms of machine learning. This makes it highly adaptive and allows it to adjust when new information becomes available. In this way, a reinforcement learner can adapt as time goes on without human intervention. Now I am willing to visit http://www.aussiessay.com/ website to get help in my essay that I want to write about this difficult topic.
Write your own review or comment: