citeseer |
(0) (0 Votes)
|
Views: (1022) Date: (15-05-09) Pages: () |
Abstract: How can we guarantee that our software and robotic agents will behave as we require, even after learning? Formal verification should play a key role but can be computationally expensive, particularly if re-verification follows each instance of learning. This is especially a problem if the agents need to make rapid decisions and learn quickly while online.