Show simple item record

dc.contributor.authorThompson, Tommy
dc.contributor.authorLevine, John
dc.date.accessioned2013-11-04T14:16:17Z
dc.date.available2013-11-04T14:16:17Z
dc.date.issued2009-08
dc.identifier.doi10.1109/CIG.2009.5286456
dc.description.abstractApplying neural networks to generate robust agent controllers is now a seasoned practice, with time needed only to isolate particulars of domain and execution. However we are often constrained to local problems due to an agents inability to reason in an abstract manner. While there are suitable approaches for abstract reasoning and search, there is often the issues that arise in using offline processes in real-time situations. In this paper we explore the feasibility of creating a decentralised architecture that combines these approaches. The approach in this paper explores utilising a classical automated planner that interfaces with a library of neural network actuators through the use of a Prolog rule base. We explore the validity of solving a variety of goals with and without additional hostile entities as well as added uncertainty in the the world. The end results providing a goal driven agent that adapts to situations and reacts accordingly.
dc.language.isoenen
dc.publisherComputational Intelligence and Games, 2009. CIG 2009. IEEE Symposium onen
dc.relation.urlhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5286456en
dc.subjectPlanning in gamesen
dc.subjectArtificial neural networksen
dc.titleRealtime execution of automated plans using evolutionary roboticsen
dc.typeOtheren
dc.contributor.departmentUniversity of Strathclydeen
refterms.dateFOA2019-02-28T13:16:03Z
html.description.abstractApplying neural networks to generate robust agent controllers is now a seasoned practice, with time needed only to isolate particulars of domain and execution. However we are often constrained to local problems due to an agents inability to reason in an abstract manner. While there are suitable approaches for abstract reasoning and search, there is often the issues that arise in using offline processes in real-time situations. In this paper we explore the feasibility of creating a decentralised architecture that combines these approaches. The approach in this paper explores utilising a classical automated planner that interfaces with a library of neural network actuators through the use of a Prolog rule base. We explore the validity of solving a variety of goals with and without additional hostile entities as well as added uncertainty in the the world. The end results providing a goal driven agent that adapts to situations and reacts accordingly.


Files in this item

Thumbnail
Name:
cig2009_045e.pdf
Size:
274.0Kb
Format:
PDF
Description:
Conference paper, publishers PDF.

This item appears in the following Collection(s)

Show simple item record