36 search results - page 1 / 8 » Reinforcement Learning as Classification: Leveraging Modern ... |
ICML
2003
IEEE
14 years 4 months ago
2003
IEEE
ACL
2007
14 years 11 days ago
2007
On a multi-dimensional text categorization task, we compare the effectiveness of a feature based approach with the use of a stateof-the-art sequential learning technique that has ...
ICML
2005
IEEE
14 years 11 months ago
2005
IEEE
We prove a quantitative connection between the expected sum of rewards of a policy and binary classification performance on created subproblems. This connection holds without any ...
ICML
2003
IEEE
14 years 11 months ago
2003
IEEE
This paper addresses the problem of classification in situations where the data distribution is not homogeneous: Data instances might come from different locations or times, and t...
Publication
Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schem...