Show simple item record

dc.contributor.advisorO'Riordan, Colm
dc.contributor.authorCunningham, Alan
dc.date.accessioned2013-10-23T15:26:04Z
dc.date.available2013-10-23T15:26:04Z
dc.date.issued2013-09-27
dc.identifier.urihttp://hdl.handle.net/10379/3771
dc.description.abstractThis thesis concerns the creation of groups of characters which, through the use simple actions, cooperate and coordinate to survive together. These groups are created automatically using Evolutionary Computation methods. A Common Pool Resource dilemma is chosen from the social science and economic literature which models a group's use of a shared resource. Previous studies of human behaviours with this game environment allow for the comparison of the automatically generated solutions against expected behaviours and human performance. It is shown that by introducing irrationality into the solution creation, human-like play can be generated automatically. The traditional dilemmas are expanded by introducing notions of spatiality and the notion of character roles. This provides several benefits including modelling a familiar convention within computer games as well as providing context based constraints for the evolutionary process. The group behaviours being created must now involve cooperation and coordination, as individuals within the group try to survive in the abstract game world. A range of parameters and their effects are shown on the creation of group behaviours in this abstract game environment. A selection of parameters is chosen to illustrate the behaviours possible under various conditions. Simulated dynamic elements, derived from likely interactions or experiences an AI character may encounter in a computer game, are introduced. A simulated computer game environment is created to assess the performance of group behaviours created in an abstract world. By using various selection criteria, it is shown that solutions automatically created in an abstract environment can, without much modification or translation, be suitable for a computer game environment. It is also shown that, by using an appropriate environment, the application of simple individual actions can lead to group behaviours that exhibit both cooperation and coordination in order to survive in a changing world.en_US
dc.subjectGenetic Programmingen_US
dc.subjectArtificial Intelligenceen_US
dc.subjectComputer Gamesen_US
dc.subjectEvolutionary Computationen_US
dc.subjectCommon Pool Resourceen_US
dc.subjectCollege of Engineering and Informaticsen_US
dc.titleEvolution of Groups for Common Pool Resource Sharingen_US
dc.typeThesisen_US
dc.contributor.funderCollege of Engineering and Informatics Fellowshipen_US
dc.local.noteThis thesis concerns the automatic creation of behaviours for individuals in various group structures. These individuals learn to cooperate and coordinate their actions in order to create a resource that sustains their life. Applications of the behaviours are compared to human behaviours and are demonstrated in a computer game environment.en_US
dc.local.finalYesen_US
nui.item.downloads981


Files in this item

Attribution-NonCommercial-NoDerivs 3.0 Ireland
This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. Please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.

The following license files are associated with this item:

Thumbnail

This item appears in the following Collection(s)

Show simple item record