12194 search results - page 240 / 2439 » Numberings Optimal for Learning |
192
click to vote
UAI
2003
15 years 8 months ago
2003
For a given problem, the optimal Markov policy over a finite horizon is a conditional plan containing a potentially large number of branches. However, there are applications wher...
150
click to vote
VLDB
1995
ACM
15 years 10 months ago
1995
ACM
Traditionally, optimizers are “programmed” to optimize queries following a set of buildin procedures. However, optimizers should be robust to its changing environment to gener...
178
click to vote
ICML
2004
IEEE
16 years 7 months ago
2004
IEEE
We consider learning in a Markov decision process where we are not explicitly given a reward function, but where instead we can observe an expert demonstrating the task that we wa...
171
click to vote
IPPS
2005
IEEE
16 years 4 days ago
2005
IEEE
The problem of radio channel assignments with multiple levels of interference can be modeled using graph theory. Given a graph G, possibly infinite, and real numbers k1, k2, . . ...
176
click to vote
ICML
2005
IEEE
16 years 7 months ago
2005
IEEE
We consider reinforcement learning in systems with unknown dynamics. Algorithms such as E3 (Kearns and Singh, 2002) learn near-optimal policies by using "exploration policies...