Key points are not available for this paper at this time.
Our work with the AAANTS (adaptive, autonomous, agent colony interactions with network transparent services) project attributes to developing methodologies for demonstrating collective intelligent behaviour in agent-based synthetic ecosystems. The model gains wisdom from a very successful community life style found in the animal kingdom - the Ants. The proposed model is a multiagent system that conceptualises and implements a colony of agents that actively interact with a collection of distributed services in order to provide adaptive behaviour. We have implemented the AAANTS model on an intelligent environment related project and built a prototype for an intelligent room that actively adapts the environmental conditions based on user behavioural patterns. We discuss the knowledge representation based on "Frames" that harmonise with continuous adaptation based on reinforcement learning techniques.
Ranasinghe et al. (Tue,) studied this question.