8381 search results - page 371 / 1677 » The security of machine learning |
175
click to vote
ICML
1998
IEEE
16 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...
219
click to vote
ICML
1998
IEEE
16 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...
203
click to vote
ICML
1998
IEEE
16 years 7 months ago
1998
IEEE
This paper introduces the RL-TOPs architecture for robot learning, a hybrid system combining teleo-reactive planning and reinforcement learning techniques. The aim of this system ...
172
click to vote
ICML
1997
IEEE
16 years 7 months ago
1997
IEEE
Explanation-Based Reinforcement Learning (EBRL) was introduced by Dietterich and Flann as a way of combining the ability of Reinforcement Learning (RL) to learn optimal plans with...
167
click to vote
ICML
1996
IEEE
16 years 7 months 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)...