275 search results - page 18 / 55 » Improved Guarantees for Learning via Similarity Functions |
74
Voted
ATAL
2006
Springer
15 years 1 months ago
2006
Springer
We contribute Policy Reuse as a technique to improve a reinforcement learning agent with guidance from past learned similar policies. Our method relies on using the past policies ...
74
Voted
STOC
2003
ACM
15 years 10 months ago
2003
ACM
We consider a fundamental problem in computational learning theory: learning an arbitrary Boolean function which depends on an unknown set of k out of n Boolean variables. We give...
BMCBI
2008
14 years 9 months ago
2008
Background: Accurate peptide identification is important to high-throughput proteomics analyses that use mass spectrometry. Search programs compare fragmentation spectra (MS/MS) o...
99
Voted
ATAL
2010
Springer
14 years 10 months ago
2010
Springer
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...
KDD
2008
ACM
15 years 10 months ago
2008
ACM
A large fraction of the URLs on the web contain duplicate (or near-duplicate) content. De-duping URLs is an extremely important problem for search engines, since all the principal...