Power and Limits of Reactive Agents

In this paper I will show how reactive agents can solve relatively complex tasks without requiring any internal state and I will demonstrate that this is due to their ability to coordinate perception and action. By acting (i.e. by modifying their position with respect to the external environment and/or the external environment itself), agents partially determine the sensory patterns they receive from the environment. As I will show, agents can take advantage of this ability to: (1) select sensory patterns that are not affected by the aliasing problem and avoiding those that are; (2) select sensory patterns in which groups of patterns requiring different answers do not strongly overlap; (3) exploit the fact that, given a certain behavior, sensory states might indirectly encode information about useful features of the environment; (4) exploit emergent behaviors resulting from a sequence of sensory-motor loops and from the interaction between the robot and the environment. Finally I will discuss the relation between pure reactive agents and pure representational agents and I will argue that a large variety of intermediate cases between these two extremes exists. In particular I will discuss the case of agents which encode in their internal states what they did in the previous portion of their lifetime which, given a certain behavior, might indirectly encode information about the external environment.