3274 search results - page 31 / 655 » Using Learning in a Control Agent |
INFOSCALE
2006
ACM
14 years 1 months ago
2006
ACM
This research addresses the formation of new concepts and their corresponding ontology in a multiagent system where individual autonomous agents try to learn new concepts by consu...
ATAL
2010
Springer
13 years 8 months ago
2010
Springer
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...
ISORC
2000
IEEE
14 years 4 days ago
2000
IEEE
This paper documents progress to date on a research project, the goal of which is wartime event prediction. The paper describes the operational concept, the datamining environment...
IJCNN
2008
IEEE
14 years 2 months ago
2008
IEEE
— The first-person-shooter Quake II is used as a platform to test neuro-visual control and retina input layouts. Agents are trained to shoot a moving enemy as quickly as possibl...
AIIDE
2008
13 years 10 months ago
2008
Human experience with interactive games will be enhanced if the software agents that play the game learn from their failures. Techniques such as reinforcement learning provide one...