Neural networks against genetic algorithms for negotiating agent behaviour prediction

The design and evaluation of agents handling automated negotiations on behalf of their human or corporate owners is a quite challenging research field. This paper proposes to enhance such agents with learning techniques, in order to achieve more profitable results for the parties they represent. The proposed learning techniques are based on MLP or RBF neural networks (NNs) and are quite lightweight. Alternatively, the agents use Genetic Algorithms (GAs) to predict the behaviour of their opponents. All designed approaches aim to reduce the cases of unsuccessful negotiations and maximize the client's utility. The designed NN- and GA-assisted negotiation strategies have been compared and empirically evaluated via numerous experiments. This work has in part been supported by the project “Amigo - Ambient intelligence for the networked home environment”. The Amigo project is funded by the European Commission as an integrated project (IP) in the Sixth Framework Programme under the contract number IST 004182. For more information you may refer to www.amigo-project.org.