38 search results - page 3 / 8 » icml 1998 |
ICML
1998
IEEE
14 years 7 months ago
1998
IEEE
Relational reinforcement learning (RRL) is both a young and an old eld. In this paper, we trace the history of the eld to related disciplines, outline some current work and promis...
ICML
1998
IEEE
14 years 7 months ago
1998
IEEE
Similarity is an important and widely used concept. Previous definitions of similarity are tied to a particular application or a form of knowledge representation. We present an in...
ICML
1998
IEEE
13 years 10 months ago
1998
IEEE
We present and solve a real-world problem of learning to drive a bicycle. We solve the problem by online reinforcement learning using the Sarsa( )-algorithm. Then we solve the ...
ICML
1998
IEEE
14 years 7 months ago
1998
IEEE
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
ICML
1998
IEEE
14 years 7 months ago
1998
IEEE
This paper shows how a text classifier's need for labeled training documents can be reduced by taking advantage of a large pool of unlabeled documents. We modify the Query-by...