SummaryudMulti-Agent systems typically utilise simple, predictable agents. The usage of such agentsudin large systems allows for complexity to be achieved through the interaction of theseudagents. It is feasible, however, to utilise intelligent agents in smaller systems, allowing forudmore agent complexity and hence a higher degree of realism in the multi-agent model. Byudutilising the TD( ) Algorithm to train feedforward neural networks, intelligent agentsudwere successfully trained within the reinforcement learning paradigm. A methodology forudstabilising this typically unstable neural network training was found through first lookingudat the relatively simple problem of Tic-Tac-Toe. Once a stable training methodology wasudarrived at, the more complex task of tackling a multi-player, multi-stage card-game wasudtackled. The results illustrated that a variety of scenarios can be realistically investigatedudthrough the multi-agent model, allowing for solving of situations and betterudunderstanding of the game itself. Yet more startling, owing to the agent’s design, theudagents learned on their own to bluff, giving much greater insight into the nature ofudbluffing in such games that lend themselves to the act.
展开▼
