Claudia V. Goldman and Jeffrey S. Rosensehein
We investigate how agents can learn to become experts, and eventually organize themselves appropriately for a range of tasks. Our aim is to look at evolutionary processes that lead to organizations of experts. The distributed artificial intelligence (DAI) community has dealt with multiagent systems that organize themselves in order to achieve a specific shared goal. Various organizations can arise that will effectively balance the load on the agents and improve their performance. We here look at the process of emergence of an organization as a step that takes place prior to the execution of a task, and as a general process related to a range of problems in a domain. To explore the ideas set forward, we designed and implemented a testbed based on the idea of the game of Life. We present experimental results that show different patterns of organizations that might evolve in a multiagent system.