5 search results - page 1 / 1 » icml 1992 |
ICML
1992
IEEE
13 years 9 months ago
1992
IEEE
ICML
2007
IEEE
14 years 5 months ago
2007
IEEE
It is often thought that learning algorithms that track the best solution, as opposed to converging to it, are important only on nonstationary problems. We present three results s...
ICML
1995
IEEE
14 years 5 months 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
1994
IEEE
13 years 8 months ago
1994
IEEE
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
ICML
1996
IEEE
14 years 5 months ago
1996
IEEE
Some of the most successful recent applications of reinforcement learning have used neural networks and the TD algorithm to learn evaluation functions. In this paper, we examine t...