Learning for distributed artificial intelligence systems

In the context of improving the performance of a group of agents, allowing individual agents to improve their performance may not be enough to improve the performance of the group. To apply learning to the overall group performance the agents need to adapt and learn to work with each other. Indeed, the agents may not need to learn more about the domain, as in the traditional sense of machine learning, to improve group performance. In fact, to improve the performance of the group, the agents may only need to learn to work together and not necessarily improve their individual performance. In addition, not all of the agents must be able to learn or adapt to allow the group to improve. This papers examines the learning potential for different dimensions of distributed artificial intelligence systems. It concerns adaptation and learning at the knowledge and organizational levels. Several existing systems are examined and classified according to the dimensions for learning. The paper does not examine general dimensions for DAI, but only those dimensions that can be used for examining learning in a DAI system