Abstract | ||
---|---|---|
In this paper we further explore the potential of a decentralised controller architecture that places multi-layer perceptrons within a subsumption hierarchy. Previous research exploring this approach proved successful in generating agents that could solve problems while coping with new reactive stimuli. However there were many unresolved questions that we wished to explore. In this paper we explore the use of our architecture with iterative training, increased controller modularity and conflicting goals. Results provide some interesting insights into the potential this method could have to agent designers. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/CIG.2009.5286452 | CIG |
Keywords | Field | DocType |
improving control,multi-layer perceptrons,agent designer,iterative training,interesting insight,decentralised controller architecture,previous research,increased controller modularity,new reactive stimulus,conflicting goal,evotanks domain,subsumption hierarchy,iterative methods,process control,multi agent systems,data mining,games,navigation,multi layer perceptron,artificial neural networks,multilayer perceptron | Architecture,Control theory,Iterative method,Computer science,Simulation,Multi-agent system,Process control,Artificial intelligence,Artificial neural network,Hierarchy,Modularity,Machine learning | Conference |
Citations | PageRank | References |
5 | 0.43 | 4 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tommy Thompson | 1 | 78 | 8.28 |
Fraser Milne | 2 | 5 | 0.43 |
Alastair Andrew | 3 | 5 | 0.77 |
John Levine | 4 | 96 | 11.96 |