http://www.cl.cam.ac.uk/techreports/UCAM-CL-TR-273.pdf http://citeseer.ist.psu.edu/302165.html
How far is it from hybrid agent architecture to integrative artificial intelligence? I don't necessarily mean artificial general intelligence. Hybrid architecture seems to be pre-integrative: it doesn't need a uniform representation to span across the system. Learning seems to be local to modules (no meta-learning), but the learned stuff is coordinated with the whole system (some limited meta-learning). Do autonomous agents "really" need AGI? Best regards. ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=231415&user_secret=fabd7936
