We present a concept to use off-line learning approaches to achieve on-line learning of cooperative behavior of agents and instantiate this concept for evolutionary learning with agents based on prototype situation-action-pairs and the nearest-neighbor rule. For such an agent model also modeling of other agents can be achieved using the agent's own architecture with situation-action-pairs derived from observations. We tested our on-line learning agents for different variants of the pursuit game and characterize the aspects of variants for which our on-line learning agents outperform off-line learning ones. Since our concept also allows a smooth transition from off-line learning to on-line learning and vice versa, the resulting system is able to win much more game variants than systems using either on- or off-line learning exclusively.
Generated: 04/07/2000