How to Do the Right Thing
dc.date.accessioned | 2004-10-04T14:35:51Z | |
dc.date.accessioned | 2018-11-24T10:11:31Z | |
dc.date.available | 2004-10-04T14:35:51Z | |
dc.date.available | 2018-11-24T10:11:31Z | |
dc.date.issued | 1989-10-01 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/6013 | |
dc.identifier.uri | http://repository.aust.edu.ng/xmlui/handle/1721.1/6013 | |
dc.description.abstract | This paper presents a novel approach to the problem of action selection for an autonomous agent. An agent is viewed as a collection of competence modules. Action selection is modeled as an emergent property of an activation/inhibition dynamics among these modules. A concrete action selection algorithm is presented and a detailed account of the results is given. This algorithm combines characteristics of both traditional planners and reactive systems: it produces fast and robust activity in a tight interaction loop with the environment, while at the same time allowing for some prediction and planning to take place. | en_US |
dc.format.extent | 51 p. | en_US |
dc.format.extent | 4087213 bytes | |
dc.format.extent | 3188021 bytes | |
dc.language.iso | en_US | |
dc.title | How to Do the Right Thing | en_US |
Files in this item
Files | Size | Format | View |
---|---|---|---|
AIM-1180.pdf | 3.188Mb | application/pdf | View/ |
AIM-1180.ps | 4.087Mb | application/postscript | View/ |