Closed-Loop Learning of Visual Control Policies
In this dissertation, I introduce a general, flexible framework for learning direct mappings from images to actions in an agent that interacts with its surrounding environment. This work is motivated by the paradigm of purposive vision. The original contributions consist in the design of reinforceme...
Main Author: | |
---|---|
Other Authors: | |
Format: | Others |
Published: |
Universite de Liege
2006
|
Subjects: | |
Online Access: | http://bictel.ulg.ac.be/ETD-db/collection/available/ULgetd-12072006-100239/ |