3274 search results - page 147 / 655 » Using Learning in a Control Agent |
110
click to vote
AAAI
2008
15 years 4 months ago
2008
In this paper, we study a sequential decision making problem. The objective is to maximize the average reward accumulated over time subject to temporal cost constraints. The novel...
159
click to vote
KBSE
2002
IEEE
15 years 7 months ago
2002
IEEE
Engineering individual components of a multi-agent system and their interactions is a complex and error-prone task in urgent need of methods and tools. Prototyping is a valuable t...
103
Voted
ATAL
2004
Springer
15 years 7 months ago
2004
Springer
We studied the role of the competence of an interface agent that helped users to learn and use a text editor. Participants in the study made a set of changes to a document with th...
112
Voted
FQAS
2009
Springer
14 years 12 months ago
2009
Springer
In this paper, an agent is defined as a triple (S, RS, LS), where S is a multi-hierarchical decision system, RS is a set of rules extracted from S defining values of its decision a...
115
click to vote
CORR
2007
Springer
15 years 2 months ago
2007
Springer
—We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence futu...