22 search results - page 5 / 5 » Contextual Multi-Armed Bandits |
ICML
2008
IEEE
14 years 6 months ago
2008
IEEE
We examine the problem of evaluating a policy in the contextual bandit setting using only observations collected during the execution of another policy. We show that policy evalua...
CORR
2011
Springer
12 years 9 months ago
2011
Springer
We study decision making in environments where the reward is only partially observed, but can be modeled as a function of an action and an observed context. This setting, known as...