Collective Memory Search: Exploiting an Information Center for Exploration

Complex group behavior arises in social insects colonies as the integration of the actions of simple and redundant individual insects Adler and Gordon, 1992, Oster and Wilson, 1978]. Furthermore, the colony can act as an information center to expedite foraging Brown, 1989]. We apply these lessons from natural systems to model collective action and memory in a computational agent society. Collective action can expedite search in combinatorial optimization problems Dorigo et al., 1996]. Collective memory can improve learning in multiagent systems Garland and Alterman, 1996]. We integrate the simplicity of collective action with the pattern detection of collective memory to sig-niicantly improve both the gathering and processing of knowledge. We investigate the augmentation of distributed search in genetic programming based systems with collective memory. Four models of collective memory search are deened based on the interaction of the search agents and the process agents which manipulate the collective memory. We present implementations of the collective memory search models and further show how collective memory search facilitates \scaling up" in a problem domain. An Active-Passive model, which gathers results from the independent searchers, is examined and found to provide a springboard from which search agents can extend their exploration. A Passive-Active model, in which the gathered results are collated, is employed by the process agents to piece together the solution from the parts collected by the search agents. An Active-Active model, in which the gathered results are collated and returned back to the search agents, allows the search agents to eeectively explore the search space while the process agents concurrently search and manipulate the much smaller collective memory space.