ICML
1995
IEEE
15 years 14 days ago
1995
IEEE
The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
ICML
1995
IEEE
15 years 14 days ago
1995
IEEE
In this paper we introduce Ant-Q, a family of algorithms which present many similarities with Q-learning (Watkins, 1989), and which we apply to the solution of symmetric and asymm...
ICML
1995
IEEE
15 years 14 days ago
1995
IEEE
ICML
1995
IEEE
15 years 14 days ago
1995
IEEE
Understanding high-dimensional real world data usually requires learning the structure of the data space. The structure maycontain high-dimensional clusters that are related in co...
ICML
1995
IEEE
15 years 14 days ago
1995
IEEE
A number of reinforcement learning algorithms have been developed that are guaranteed to converge to the optimal solution when used with lookup tables. It is shown, however, that ...
ICML
1996
IEEE
15 years 14 days ago
1996
IEEE
ICML
1996
IEEE
15 years 14 days ago
1996
IEEE
Generating good, production-quality plans is an essential element in transforming planners from research tools into real-world applications, but one that has been frequently overl...
ICML
1996
IEEE
15 years 14 days ago
1996
IEEE
This paper discusses the unsupervised learning problem. An important part of the unsupervised learning problem is determining the numberofconstituent groups (componentsor classes)...
ICML
1996
IEEE
15 years 14 days ago
1996
IEEE
Finding structure in multiple streams of data is an important problem. Consider the streams of data owing from a robot's sensors, the monitors in an intensive care unit, or p...
ICML
1996
IEEE
15 years 14 days ago
1996
IEEE
Research in reinforcementlearning (RL)has thus far concentrated on two optimality criteria: the discounted framework, which has been very well-studied, and the averagereward frame...