Multiagent Learning Systems and Expert Agents

This paper focuses on two main research topics we are investigating. First, we investigate how agents can learn strategic behavior in a teacher-learner model. The notion of the teacher here should be understood as a "trainer". We present the general teacher-learner model together with results from experiments performed in the traffic lights domain. Second, we investigate how agents can learn to become experts, and eventually organize themselves appropriately for a range of tasks. The model is based on evolutionary processes that lead to organizations of experts. In our case, the organization emerges as a step prior to the execution of a task, and as a general process related to a range of problems in a domain. To explore these ideas, we designed and implemented a testbed based on the idea of the game of Life.