Planning in Information Space with Macro-actions
published: Nov. 8, 2010, recorded: June 2010, views: 2854
Report a problem or upload filesIf 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.
Active learning can be framed as a planning in information space problem: the goal is to learn about the world by taking actions that improve expected performance. In some domains, planning far into the future is prohibitively expensive and the agent is not able to discover effective information-gathering plans. However, by using macro-actions consisting of fixed-length open-loop policies, the policy class considered during planning is explicitly restricted in return for computational gains that allow much deeper-horizon forward search. In a certain subset of domains, it is possible to analytically compute the distribution over posterior beliefs that results from a single macro-action; this distribution captures any observation sequence that could occur during the macro-action, and allows significant additional computational savings. I will show performance on two simulation experiments: a standard exploration domain and a UAV search domain.
Download slides: rss2010_roy_pis_01.pdf (39.7 MB)
Download rss2010_roy_pis_01.mp4 (Video - generic video source 216.6 MB)
Download rss2010_roy_pis_01.flv (Video 104.1 MB)
Download rss2010_roy_pis_01_450x360_h264.mp4 (Video 82.6 MB)
Download rss2010_roy_pis_01_600x480_h264.mp4 (Video 112.2 MB)
Download rss2010_roy_pis_01_720x576_h264.mp4 (Video 187.5 MB)
Download rss2010_roy_pis_01.wmv (Video 101.3 MB)
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !