This paper considers the use of neural networks to model bounded rational behaviour. The underlying theory and use of neural networks is now a component of various forms of scientific enquiry, be it modelling artificial intelligence, developing better pattern recognition or solving complex...

This paper presents a neural network based methodology for examining the learning of game-playing rules in never-before seen games. A network is trained to pick Nash equilibria in a set of games and then released to play a larger set of new games. While faultlessly selecting Nash equilibria in...

This paper is an extension of the paper 'The Robustness of Agent-Based Models of Electricity Wholesale Markets', EPRG1213 which was motivated by the problem of analysing market power in liberalised electricity markets. That paper examined two particular forms of agent-based models commonly used...

Agent-based modelling is an attractive way of finding equilibria in complex problems involving strategic behaviour, particularly in electricity markets with transmission constraints. However, while it may be possible to demonstrate convergence of learning behaviour to a Nash equilibrium, that is...