Abstract

The problem of action selection by autonomous agents becomes increasingly difficult when acting in continuous, non-deterministic and dynamic environments pursuing multiple and possibly conflicting goals. We propose a method that exploits additional information gained from continuous states, is able to deal with unexpected situations, and takes multiple and conflicting goals into account including additional motivational aspects such as dynamic goals, which allow for situation-dependent motivational influence on the agent. Further we show some domain independent properties of this algorithm along with empirical results gained using the RoboCup simulated soccer environment. 1

Citations

220	Situated agents can have goals - Maes - 1990
118	The dynamics of action selection - Maes - 1989
97	A multivalued logic approach to integrating planning and control - Saffiotti, Konolige, et al. - 1995
64	Soccer Server: A simulator of RoboCup - Noda - 1995
39	Learning behavior networks from experience - Maes - 1992
30	Workload -an examination of the concept - Gopher, Donchin - 1986
9	Attractors in Recurrent Behavior Networks - Goetz - 1997
7	An evaluation of Maes’ bottomup mechanism for behavior selection - Tyrrell - 1994
1	Action selection in an autonmous agent with a hierarchical distributed reactive planning architecture - Decugis, Ferber - 1998