An Evaluation of Maes's Bottom-Up Mechanism for Behavior Selection

Abstract

Maes has proposed a mechanism for action selection (behavioral choice) (Maes, 1989, 1990, 1991 a), which is reviewed here and is evaluated using a simulated environment. This simulated environment is a detailed and complex generalized model of the action selection problem faced by an animal in the wild and presents a rather severe test for an action selection mechanism. The results of testing Maes's mechanism in the simulated environment are discussed, some observed deficiencies in the mechanism's operation are described, and the computational reasons underlying the deficiencies are explained. lt is argued that some central aspects of the design of Maes's mechanism mean that it is not able to deal well with animal like action selection problems.