The Strategic Control of an Ant-Based Routing System Using Neural Net Q-Learning Agents
- 775 Downloads
Agents have been employed to improve the performance of an Ant-Based Routing System on a communications network. The Agents use a Neural Net based Q-Learning approach to adapt their strategy according to conditions and learn autonomously. They are able to manipulate parameters that effect the behaviour of the Ant-System. The Ant-System is able to find the optimum routing configuration with static traffic conditions. However, under fast-changing dynamic conditions, such as congestion, the system is slow to react; due to the inertia built up by the best routes. The Agents reduce this inertia by changing the speed of response of the Ant-System. For an effective system, the Agents must cooperate – forming an implicit society across the network.
KeywordsMobile Agent Telecommunication Network Reward Function Short Route Ideal Agent
Unable to display preview. Download preview PDF.
- Dorigo, M., Di Caro, G.: AntNet: A Mobile Agents Approach to Adaptive Routing., Technical Report IRIDIA 97-12 (1997)Google Scholar
- Kapetanakis, S., Kudenko, D.: Improving on the Reinforcement Learning of Coordination in Cooperative Multi-Agent Systems. In: Proc. AAMAS-II, AISB 2002, pp. 89–94. Imperial College, London (2002)Google Scholar
- Schoonderwoerd, R., Holland, O., Bruten, J.: Ant-Based Load Balancing in Telecommunications Networks. Hewlett-Packard Laboratories, Bristol (1996)Google Scholar
- Tesauro, G.: Pricing in Agent Economies using Neural Networks and Multi-Agent Q-Lear ning. In: Proc. Workshop ABS-3 Learning About, From and With other Agents (August 1999)Google Scholar
- Tumer, K., Wolpert, D.H.: Avoiding Braess’ Paradox through Collective Intelligence. AAAI/ IAAI (2000)Google Scholar
- Vittori, K., Araújo, F.R.: Agent-Oriented Routing in Telecommunications Networks. IEICE Transactions on Communications E84-B(11), 3006–3013 (2001)Google Scholar