3274 search results - page 308 / 655 » Using Learning in a Control Agent |
171
click to vote
AAAI
1992
15 years 8 months ago
1992
It is often useful for a robot to construct a spatial representation of its environment from experiments and observations, in other words, to learn a map of its environment by exp...
186
click to vote
ICANN
1997
Springer
15 years 11 months ago
1997
Springer
We use simulated soccer to study multiagent learning. Each team's players (agents) share action set and policy but may behave differently due to position-dependent inputs. All...
177
Voted
DBSEC
2010
15 years 8 months ago
2010
Abstract. We present a modelling language, called X-Policy, for webbased collaborative systems with dynamic access control policies. The access to resources in these systems depend...
143
Voted
C5
2007
IEEE
16 years 1 months ago
2007
IEEE
I describe my experiences as an artist in making large digital portraits along with some of the issues that make this process more exciting, and cumbersome, than picking up a penc...
171
click to vote
MATES
2007
Springer
16 years 26 days ago
2007
Springer
The most common reason for plan repair are the violation of a plan’s temporal constraints. Air Traffic Control is an example of an area in which violations of the plan’s tempo...