Behavior Networks for Continuous Domains Using Situation-Dependent Motivations

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 Introduction Agents in a complex dynamic domain need to take multiple goals into account, which may be of different type (as exemplified in the RoboCup soccer environment): ffl maintenance goals, which should be less demanding the more the goal is satisfied (e.g. 'have stamina'). ffl achievement go...