Upload

Loading...

State RB2 rewarded

34 views

Loading...

Loading...

Loading...

Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Published on Mar 25, 2012

(HD available) In this example the weights are set such that one of the robotic evadres acts like a high value target. In order to maximize its reward, the hierarchical controller allocates tasks among the agents to reassure that the high value target will be seen by the camera system.

Loading...

to add this to Watch Later

Add to

Loading playlists...