4035 search results - page 38 / 807 » Useless Actions Are Useful |
146
click to vote
ESANN
2008
15 years 7 months ago
2008
The aim of this paper is to enhance the performance of a reinforcement learning game agent controller, within a dynamic game environment, through the retention of learned informati...
216
click to vote
CADUI
2006
15 years 7 months ago
2006
We present a low-cost hand-based device coupled with a 3D motion recovery engine and 3D visualization. This platform aims at studying ergonomic 3D interactions in order to manipula...
170
click to vote
ISVC
2007
Springer
15 years 12 months ago
2007
Springer
Surveillance systems that operate continuously generate large volumes of data. One such system is described here, continuously tracking and storing observations taken from multiple...
173
click to vote
AAAI
2007
15 years 8 months ago
2007
reason with abstracted models of the behaviours they use to construct plans. When plans are turned into the instructions that drive an executive, the real behaviours interacting w...
141
click to vote
AIIDE
2008
15 years 8 months ago
2008
We introduce the ALeRT (Action-dependent Learning Rates with Trends) algorithm that makes two modifications to the learning rate and one change to the exploration rate of traditio...