Power and the limits of reactive agents

Abstract This paper shows how reactive agents can solve complex tasks without requiring any internal state and demonstrates 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. 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. The relation between pure reactive agents and pure representational agents is discussed and it is argued that a large variety of intermediate cases between these two extremes exists. In particular, attention is given to the case of agents that 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.