Friday, August 20, 2010
3:30 PM
CSB 703
Daphne Liu
Department of Computer Science, University of Rochester
A Framework for Building Self-motivated, Self-aware Agents
I'll present a framework for building self-motivated, self-aware agents that plan continuously so as to maximize long-term rewards. While such agents employ reasoned exploration of feasible sequences of actions and corresponding states, they also behave opportunistically
and recover from failure. The framework allows for both specific and general (quantified) knowledge, and for epistemic predicates such as knowing-that and knowing-whether. Because realistic agents have only partial knowledge of their world, the reasoning of the proposed agents uses a weakened closed world assumption. The planning operators allow for quantitative, gradual change and side effects such as numerical calculations and language production, using a uniform procedural attachment method. Question answering and experimental runs are shown
for our particular agent
ME in a simple world.